Author name cluster

Jie Hu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

44 papers

2 author rows

EAAI Journal 2026 Journal Article

An information-aggregated multiple-criteria design evaluation method by exploring reliability, fuzziness and divergence from uncertain linguistic preferences

Jin Qi
Haiqing Huang
Jie Hu
Yinghong Peng

This paper proposes a new information-aggregated multiple-criteria group evaluation method, by using linguistic D-number (LDN) and other uncertainty treatment approaches, named as LDN-based design evaluation with multiple information (LDN-MI). In LDN-MI, the group-level LDN-expressed preferences are generated to form the L-preference space, which capture initial linguistic preference (z) and its reliability (r) information from expert and user groups. Then, the fuzziness (f) and divergence (d) of L-preference are further explored by using rough number and information entropy. Finally, a multi-information aggregation approach is proposed to integrate with z, r, f and d. Different from classical pure preference-only method, this study presents a new evaluation principle, that is, the candidate, which is favored by decision-makers (DMs) (higher z) with reliable (higher r) and clear (lower f) decision altitudes under important criteria (higher d), is selected as the best one. A design example and empirical analysis have been carried out to validate the feasibility and superiority of LDN-MI. Experimental results show that: i) LDN-MI makes more reasonable evaluation than traditional approaches, as the advantage of the best one chosen by LDN-MI has been justified; ii) LDN-MI is robust to preference data from different DM groups, no matter expert-only, user-only or combined group; iii) LDN-MI is also robust to different classifications of important evaluation criteria; iv) the aggregation of complete z, r, f and d yields better results than those aggregating incomplete information, and the sensitiveness of LDN-MI to r, f and d depends on the differences among DMs' decisions.

AAAI Conference 2026 Conference Paper

FIND: A Simple Yet Effective Baseline for Diffusion-Generated Image Detection

Jie Li
Yingying Feng
Chi Xie
Jie Hu
Lei Tan
Jiayi Ji

The remarkable realism of images generated by diffusion models poses critical detection challenges. Current methods utilize reconstruction error as a discriminative feature, exploiting the observation that real images exhibit higher reconstruction errors when processed through diffusion models. However, these approaches require costly reconstruction computations and depend on specific diffusion models, making their performance highly model-dependent. We identify a fundamental difference: real images are more difficult to fit with Gaussian distributions compared to synthetic ones. In this paper, we propose Forgery Identification via Noise Disturbance (FIND), a novel method that requires only a simple binary classifier. It eliminates reconstruction by directly targeting the core distributional difference between real and synthetic images. Our key operation is to add Gaussian noise to real images during training and label these noisy versions as synthetic. This step allows the classifier to focus on the statistical patterns that distinguish real from synthetic images. We theoretically prove that the noise-augmented real images resemble diffusion-generated images in their ease of Gaussian fitting. Furthermore, simply by adding noise, they still retain visual similarity to the original images, highlighting the most discriminative distribution-related features. The proposed FIND improves performance by 11.7% on the GenImage benchmark while running 126x faster than existing methods. By removing the need for auxiliary diffusion models and reconstruction, it offers a practical, efficient, and generalizable way to detect diffusion-generated content.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution

Xiao He
Zhijun Tu
Kun Cheng
Mingrui Zhu
Jie Hu
Nannan Wang
Xinbo Gao

The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their adaptation to diverse domains. In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models through Low-Rank Adaptation (LoRA) module to reconstruct high-resolution (HR) images. However, these dense Real-ISR models are limited in their ability to adaptively capture the heterogeneous characteristics of complex real-world degraded samples or enable knowledge sharing between inputs under equivalent computational budgets. To address this, we investigate the integration of sparse MoE into Real-ISR and propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution. We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert. This design enables flexible knowledge recombination while isolating fixed-position ranks as shared experts to preserve common-sense features and minimize routing redundancy. Furthermore, we develop a degradation estimation module leveraging CLIP embeddings and predefined positive-negative text pairs to compute relative degradation scores, dynamically guiding expert activation. To better accommodate varying sample complexities, we incorporate zero-expert slots and propose a degradation-aware load-balancing loss, which dynamically adjusts the number of active experts based on degradation severity, ensuring optimal computational resource allocation. Comprehensive experiments validate our framework's effectiveness and state-of-the-art performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

ViType: High-Fidelity Visual Text Rendering via Glyph-Aware Multimodal Diffusion

Lishuai Gao
Jun-Yan He
Yingsen Zeng
Yujie Zhong
Xiaopeng Sun
Jie Hu
Zan Gao
Xiaoming Wei

Current text-to-image models face challenges in visual text rendering: text encoders like CLIP and T5 lack glyph-level understanding and often struggle to distinguish between the specific words to be rendered and their intended semantic meaning within prompts. In addition, inconsistencies between the base model and its plugins further compromise the quality of synthesized images. In this paper, we enhance the existing text-to-image method by addressing the following aspects: (1) Text-Glyph Alignmentin a Visual Question Answering (VQA) manner to enable glyph understanding for the text encoder. This involves establishing an explicit alignment between the representations of the glyphs and their detailed attribute descriptions, which boosts the model's ability to capture fine-grained visual features of the text. (2) Accurate and harmony visual text rendering: integrating pre-aligned glyph-visual embeddings with semantic text tokens through the Multimodal Diffusion Transformer(MMDiT) synchronously, ensuring coherent feature alignment and enhancing both the robustness and fidelity of visual text rendering. (3) Image Aesthetic Refinement: leveraging a multisource data training strategy that incorporates diverse, high-quality image-text pairs from various domains, exposing the model to extensive linguistic and visual diversity while maintaining superior aesthetic quality throughout training. Our experiments demonstrate that the proposed approach significantly outperforms the existing state-of-the-art method.

PDF Details DOI

EAAI Journal 2025 Journal Article

A transfer learning-based plate shape prediction model with limited samples for roller quenching process

Wen Zhang
Min Wu
Sheng Du
Luefeng Chen
Jie Hu
Naoyuki Kubota

Plate shape is an important indicator in roller quenching process and significantly affects the using performance of steel plates. However, due to the high cost of plate shape detectors, although plate shape detectors play a vital role, many roller quenching production lines still operate without them. This issue severely limits the effectiveness of plate shape control methods and indirectly leads to a decline in plate shape quality. To address this gap and enable automatic feedback in scenarios lacking such detectors, this paper analyzes the limitations in both the accuracy and quantity of samples, and proposes a transfer learning-based plate shape prediction model. Firstly, a data augmentation module is proposed, and a deep sets module is designed for initial feature extraction. Then, a multilayer perceptron module is designed for deep feature extraction, aiming to enhance the ability of the model to capture nonlinear relationships. Next, an improved residual network module is designed to predict the plate shape. Through the special design of the model structure, the problem of different representation methods of plate shape is addressed. Finally, a targeted transfer learning strategy is designed for the proposed model to improve the accuracy in the absence of plate shape detectors. The experimental results demonstrate that the proposed model and strategy achieve high-accuracy plate shape prediction with limited samples, providing a practical plate shape prediction approach tailored for production lines without plate shape detectors.

TIST Journal 2025 Journal Article

Adaptive Target-Oriented Tracking

Sixian Chan
Xianpeng Zeng
Zhoujian Wu
Yu Wang
Xiaolong Zhou
Tinglong Tang
Jie Hu

The current one-stream tracking pipelines are early relation modeling in feature extraction. However, insufficient discrimination may result in ambiguous relation modeling during early feature extraction. Moreover, the non-target information occupies most of the search image, rendering most relation modeling futile. To tackle the above issues, we propose tracking via learning adaptive target-oriented representation, named ATOTrack. We design an Untied positional encoding to mark the template token and the search region token separately, which reduces the confused relationship between the template and the search region. Besides, we introduce an Auto-Mask Learner to decouple the target and non-target information in the search region. Interestingly, the Auto-Mask Learner can self-learn and mask the ineffective information to interpret adaptive target-oriented representation. Extensive experiments demonstrate that ATOTrack is superior to existing methods, which achieves the state-of-the-art performance on six tracking benchmarks. In particular, ATOTrack establishes a new record on AViST with 57% AO. The code and models will be released as soon.

JMLR Journal 2025 Journal Article

DisC2o-HD: Distributed causal inference with covariates shift for analyzing real-world high-dimensional data

Jiayi Tong
Jie Hu
George Hripcsak
Yang Ning
Yong Chen

High-dimensional healthcare data, such as electronic health records (EHR) data and claims data, present two primary challenges due to the large number of variables and the need to consolidate data from multiple clinical sites. The third key challenge is the potential existence of heterogeneity in terms of covariate shift. In this paper, we propose a distributed learning algorithm accounting for covariate shift to estimate the average treatment effect (ATE) for high-dimensional data, named DisC2o-HD. Leveraging the surrogate likelihood method, our method calibrates the estimates of the propensity score and outcome models to approximately attain the desired covariate balancing property, while accounting for the covariate shift across multiple clinical sites. We show that our distributed covariate balancing propensity score estimator can approximate the pooled estimator, which is obtained by pooling the data from multiple sites together. The proposed estimator remains consistent if either the propensity score model or the outcome regression model is correctly specified. The semiparametric efficiency bound is achieved when both the propensity score and the outcome models are correctly specified. We conduct simulation studies to demonstrate the performance of the proposed algorithm; additionally, we conduct an empirical study to present the readiness of implementation and validity. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

AAAI Conference 2025 Conference Paper

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

Yunshuai Zhou
Junbo Qiao
Jincheng Liao
Wei Li
Simiao Li
Jiao Xie
Yunhang Shen
Jie Hu

Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state and dynamically adjust the distilled solution space using contrastive learning. Additionally, we also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models. Note that the proposed DCKD is a structure-agnostic distillation framework, which can adapt to different backbones and can be combined with methods that optimize upper-bound constraints to further enhance model performance. Extensive experiments demonstrate that DCKD significantly outperforms the state-of-the-art KD methods across various image restoration tasks and backbones.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Effective Diffusion Transformer Architecture for Image Super-Resolution

Kun Cheng
Lei Yu
Zhijun Tu
Xiao He
Liyu Chen
Yong Guo
Mingrui Zhu
Nannan Wang

Recent advances indicate that diffusion model holds great promise in image super-resolution. While latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore transformers, which have demonstrated remarkable performance in image generation. In this work, we design an effective diffusion transformer for image super resolution (DiT-SR) that achieves the visual quality of prior-based methods, but through a training-from-scratch manner. In practice, DiT-SR leverages an overall U-shaped architecture, and adopts uniform isotropic design for all the transformer blocks across different stages. The former facilitates multi-scale hierarchical feature extraction, while the latter reallocate the computational resources to critical layers to further enhance performance. Moreover, we thoroughly analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module, enhancing the model's capacity to process distinct frequency information at different time steps. Extensive experiments demonstrate that DiT-SR outperforms the existing training-from-scratch diffusion-based SR methods significantly, and even beats some of the prior-based methods on pretrained Stable Diffusion, proving the superiority of diffusion transformer in image super resolution.

PDF Details DOI

AAAI Conference 2025 Conference Paper

EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation

Hongwei Niu
Jie Hu
Jianghang Lin
Guannan Jiang
Shengchuan Zhang

Open-vocabulary panoptic segmentation aims to segment and classify everything in diverse scenes across an unbounded vocabulary. Existing methods typically employ two-stage or single-stage framework. The two-stage framework involves cropping the image multiple times using masks generated by a mask generator, followed by feature extraction, while the single-stage framework relies on a heavyweight mask decoder to make up for the lack of spatial position information through self-attention and cross-attention in multiple stacked Transformer blocks. Both methods incur substantial computational overhead, thereby hindering the efficiency of model inference. To fill the gap in efficiency, we propose EOV-Seg, a novel single-stage, shared, efficient, and spatialaware framework designed for open-vocabulary panoptic segmentation. Specifically, EOV-Seg innovates in two aspects. First, a Vocabulary-Aware Selection (VAS) module is proposed to improve the semantic comprehension of visual aggregated features and alleviate the feature interaction burden on the mask decoder. Second, we introduce a Two-way Dynamic Embedding Experts (TDEE), which efficiently utilizes the spatial awareness capabilities of ViT-based CLIP backbone. To the best of our knowledge, EOV-Seg is the first open-vocabulary panoptic segmentation framework towards efficiency, which runs faster and achieves competitive performance compared with state-of-the-art methods. Specifically, with COCO training only, EOV-Seg achieves 24.5 PQ, 32.1 mIoU, and 11.6 FPS on the ADE20K dataset and the inference time of EOV-Seg is 4-19 times faster than state-of-the-art methods. Especially, equipped with ResNet50 backbone, EOV-Seg runs 23.8 FPS with only 71M parameters on a single RTX 3090 GPU.

PDF Details DOI

JBHI Journal 2025 Journal Article

Generalized Cross-Domain Framework for Gesture Recognition via Wrist-Worn Sensing

Shuo Zhang
Jin Qi
Duidi Wu
Qianyou Zhao
Jie Hu

Wearable sensing technology offers a natural and convenient means of human-computer interaction, particularly for gesture recognition, yet domain shifts in wrist-worn single-site sensing pose significant challenges for cross-domain gesture recognition. To address this, we proposed a generalized cross-domain framework for fine-grained gesture recognition using wrist-worn single-site sensing. Concretely, we presented a Multi-Branch Network, which combines feature-level multimodal fusion with enhanced inter-modal interaction to effectively capture fine-grained gestures. To this end, we constructed a multimodal dataset, which comprises fifteen static and eighteen dynamic gestures. Furthermore, we developed five fine-tuning strategies and evaluated them across the paradigms of cross-session, cross-subject, cross-gesture, and cross-modality. Through comprehensive analyses, this study provides valuable insights into the selection of optimal fine-tuning strategies and elucidates the internal mechanisms underlying multiple cross-domain paradigms. To investigate the intricate trade-off between recognition accuracy and computational cost, we applied nonlinear least squares to construct the Accuracy-Cost trade-off functions. Experimental findings indicated that the optimal transfer learning ratios for these cross-domain paradigms ranged from 6. 1% to 9. 0%, with most clustering around 9. 0%, offering a valuable reference for determining optimal transfer learning ratios within diverse cross-domain scenarios. Additionally, we implemented a real-time online gesture recognition system, validating the feasibility of our approach through preliminary tests in real-world scenarios. In conclusion, this study serves as a preliminary investigation into the application of wrist-worn single-site sensing for fine-grained gesture recognition.

AAAI Conference 2025 Conference Paper

GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization

Yirui Chen
Xudong Huang
Quan Zhang
Wei Li
Mingjian Zhu
Qiangyu Yan
Simiao Li
Hanting Chen

The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL). However, the lack of a large-scale data foundation makes the IMDL task unattainable. In this paper, we build a local manipulation data generation pipeline that integrates the powerful capabilities of SAM, LLM, and generative models. Upon this basis, we propose the GIM dataset, which has the following advantages: 1) Large scale, GIM includes over one million pairs of AI-manipulated images and real images. 2) Rich image content, GIM encompasses a broad range of image classes. 3) Diverse generative manipulation, the images are manipulated images with state-of-the-art generators and various manipulation tasks. The aforementioned advantages allow for a more comprehensive evaluation of IMDL methods, extending their applicability to diverse images. We introduce the GIM benchmark with two settings to evaluate existing IMDL methods. In addition, we propose a novel IMDL framework, termed GIMFormer, which consists of a ShadowTracer, Frequency-Spatial block (FSB), and a Multi-Window Anomalous Modeling (MWAM) module. Extensive experiments on the GIM demonstrate that GIMFormer surpasses the previous state-of-the-art approach on two different benchmarks.

PDF Details DOI

YNIMG Journal 2025 Journal Article

Interictal suppression in patients with mesial temporal lobe epilepsy: A simultaneous PET/fMRI study

Jie Hu
Liwei Sun
Kun Guo
Bixiao Cui
Chenyang Yao
Jingjuan Wang
Hui Ouyang
Xu Zhang

Previous stereotactic-electroencephalography (SEEG) results have suggested that seizure-onset zones (SOZs) could be suppressed by strengthened inward connectivity from the rest of the brain during interictal periods, which might explain why people with epilepsy did not have seizures continuously. However, the limited coverage of SEEG contacts and allocation bias hindered a more comprehensive survey of interictal suppression at the whole-brain level. Previous studies also lacked a direct comparison between patients and healthy controls due to the invasive nature of SEEG. In the present study, we introduced metabolic connectivity mapping (MCM), a simultaneous FDG-PET/fMRI-based measure of effective connectivity, to evaluate the inward and outward connectivity of the SOZs in patients with mesial temporal lobe epilepsy (MTLE). Specifically, simultaneous FDG-PET/fMRI data was acquired from 23 patients with left MTLE, 24 patients with right MTLE, and 25 healthy controls. At the whole-brain level, there was significant increase of inward MCM connectivity to the SOZs, which mostly came from mesial-temporo-limbic, anterior and posterior midline regions of the default mode network (DMN) and subcortical nuclei. There was also significant decrease of outward MCM connectivity from the SOZs, which mainly projected to the regions within DMN. The increased net inward MCM to the SOZs, calculated by subtracting outward MCM from the inward MCM, was positively correlated with seizure frequency. Within DMN, MTLE patients showed decreased MCM from the SOZs to posterior cingulate cortex and right ventromedial prefrontal cortex and increased effective connectivity from posterior cingulate cortex to the SOZs. Based on the MCM patterns within DMN, we were able to classify the epileptic side of MTLE with an accuracy of 91.67 % (79.17 % for MRI-negative patients). Overall, our results provide whole-brain evidences for the interictal suppression hypothesis. We also found that the regions within DMN play a critical role in the suppression of SOZs. The pattern of such suppressive network might also serve as potential features for the localization of SOZs. Our neuroimaging results does not only provide a comprehensive understanding of interictal suppression at the whole-brain level, but also shed lights on a non-invasive and time-efficient way for SOZs localization.

NeurIPS Conference 2025 Conference Paper

MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification

Yingying Feng
Jie Li
Jie Hu
Yukang Zhang
Lei Tan
Jiayi Ji

The challenge of inconsistent modalities in real-world applications presents significant obstacles to effective object re-identification (ReID). However, most existing approaches assume modality-matched conditions, significantly limiting their effectiveness in modality-mismatched scenarios. To overcome this limitation and achieve a more flexible ReID, we introduce MDReID to allow any-to-any image-level ReID systems. MDReID is inspired by the widely recognized perspective that modality information comprises both modality-shared features, predictable across modalities, and unpredictable modality-specific features, which are inherently modality-dependent and consist of two key components: the Modality Decoupling Module (MDM) and Modality-aware Metric Learning (MML). Specifically, MDM explicitly decomposes modality features into modality-shared and modality-specific representations, enabling effective retrieval in both modality-aligned and mismatched scenarios. MML, a tailored metric learning strategy, further enhances feature discrimination and decoupling by exploiting distributional relationships between shared and specific modality features. Extensive experiments conducted on three challenging multi-modality ReID benchmarks (RGBNT201, RGBNT100, MSVR310) consistently demonstrate the superiority of MDL. MDReID achieves significant mAP improvements of 9. 8\%, 3. 0\%, and 11. 5\% in modality-matched scenarios, and average gains of 3. 4\%, 11. 8\%, and 10. 9\% in modality-mismatched scenarios, respectively.

IJCAI Conference 2025 Conference Paper

Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models

Yang Zhang
Yu Yu
Bo Tang
Yu Zhu
Chuxiong Sun
Wenqiang Wei
Jie Hu
Zipeng Xie

With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However, existing alignment techniques such as RLHF or DPO often require direct fine-tuning on LLMs with billions of parameters, resulting in substantial computational costs and inefficiencies. To address this, we propose Micro token-level Accept-Reject Aligning (MARA) approach designed to operate independently of the language models. MARA simplifies the alignment process by decomposing sentence-level preference learning into token-level binary classification, where a compact three-layer fully-connected network determines whether candidate tokens are “Accepted” or “Rejected” as part of the response. Extensive experiments across seven different LLMs and three open-source datasets show that MARA achieves significant improvements in alignment performance while reducing computational costs. The source code and implementation details are publicly available at https: //github. com/IAAR-Shanghai/MARA, and the trained models are released at https: //huggingface. co/IAAR-Shanghai/MARA_AGENTS.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD

Jie Hu
Yi-Ting Ma
Young Eun

Distributed learning is essential to train machine learning algorithms across heterogeneous agents while maintaining data privacy. We conduct an asymptotic analysis of Unified Distributed SGD (UD-SGD), exploring a variety of communication patterns, including decentralized SGD and local SGD within Federated Learning (FL), as well as the increasing communication interval in the FL setting. In this study, we assess how different sampling strategies, such as i. i. d. sampling, shuffling, and Markovian sampling, affect the convergence speed of UD-SGD by considering the impact of agent dynamics on the limiting covariance matrix as described in the Central Limit Theorem (CLT). Our findings not only support existing theories on linear speedup and asymptotic network independence, but also theoretically and empirically show how efficient sampling strategies employed by individual agents contribute to overall convergence in UD-SGD. Simulations reveal that a few agents using highly efficient sampling can achieve or surpass the performance of the majority employing moderately improved strategies, providing new insights beyond traditional analyses focusing on the worst-performing agent.

PDF Details DOI

EAAI Journal 2024 Journal Article

Prediction of the transient emission characteristics from diesel engine using temporal convolutional networks

Jianxiong Liao
Jie Hu
Peng Chen
Lei Zhu
Yan Wu
Zhizhou Cai
Hanming Wu
Maoxuan Wang

In order to predict the transient emission characteristics from diesel engine accurately and quickly, a novel prediction model, based on temporal convolutional networks (TCN) that incorporates the dilated convolutions and residual connections, was presented in the paper. Firstly, 1800 samples from the World Harmonized Transient Cycle (WHTC) were employed to train and validate the model. A Random Forest algorithm was used to select six top important variables as inputs to reduce the data dimensionality. Then the effect of model hyperparameters on the prediction performance was discussed and the optimal hyperparameter combination was obtained by a particle swarm optimization (PSO) algorithm. The optimized TCN model showed a coefficient of determination value (R2) above 0. 972 for training dataset and 0. 941 for validation dataset, respectively. The root mean squared error (RMSE) and the mean absolute error (MAE) were relatively low. Finally, the measured data from World Harmonized Steady Cycle (WHSC) was used to test model, and the average R2 value of 0. 936 demonstrated that TCN model has excellent robustness and generalization. Moreover, a comparative investigation between TCN model and other advanced algorithms, including BP, GBRT, XGBoost, RNN, LSTM and Transformer, was also conducted. The result showed that TCN model has not only higher accuracy, but also has less computing time. This demonstrates that it is a promising method to predict the emission characteristics of diesel engine.

AAAI Conference 2024 Conference Paper

Real3D: The Curious Case of Neural Scene Degeneration

Dengsheng Chen
Jie Hu
Xiaoming Wei
Enhua Wu

Despite significant progress in utilizing pre-trained text-to-image diffusion models to guide the creation of 3D scenes, these methods often struggle to generate scenes that are sufficiently realistic, leading to "neural scene degeneration". In this work, we propose a new 3D scene generation model called Real3D. Specifically, Real3D designs a pipeline from a NeRF-like implicit renderer to a tetrahedrons-based explicit renderer, greatly improving the neural network's ability to generate various neural scenes. Moreover, Real3D introduces an additional discriminator to prevent neural scenes from falling into undesirable local optima, thus avoiding the degeneration phenomenon. Our experimental results demonstrate that Real3D outperforms all existing state-of-the-art text-to-3D generation methods, providing valuable insights to facilitate the development of learning-based 3D scene generation approaches.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective

Qirui Ji
Jiangmeng Li
Jie Hu
Rui Wang
Changwen Zheng
Fanjiang Xu

Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the discriminability of the invariant information. However, such methods may incur in the mis-learning of graph models towards the interpretability of graphs, and thus the learned noisy and task-agnostic information interferes with the prediction of graphs. To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature. The conducted exploratory experiments attest to the feasibility of the aforementioned roadmap. To elucidate the innate mechanism behind the performance improvement arising from the dimensional rationale, we rethink the dimensional rationale in graph contrastive learning from a causal perspective and further formalize the causality among the variables in the pre-training stage to build the corresponding structural causal model. On the basis of the understanding of the structural causal model, we propose the dimensional rationale-aware graph contrastive learning approach, which introduces a learnable dimensional rationale acquiring network and a redundancy reduction constraint. The learnable dimensional rationale acquiring network is updated by leveraging a bi-level meta-learning technique, and the redundancy reduction constraint disentangles the redundant features through a decorrelation process during learning. Empirically, compared with state-of-the-art methods, our method can yield significant performance boosts on various benchmarks with respect to discriminability and transferability. The code implementation of our method is available at https://github.com/ByronJi/DRGCL.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Self-Repellent Random Walks on General Graphs - Achieving Minimal Sampling Variance via Nonlinear Markov Chains (Extended Abstract)

Vishwaraj Doshi
Jie Hu
Do Young Eun

We consider random walks on discrete state spaces, such as general undirected graphs, where the random walkers are designed to approximate a target quantity over the network topology via sampling and neighborhood exploration in the form of Markov chain Monte Carlo (MCMC) procedures. Given any Markov chain corresponding to a target probability distribution, we design a self-repellent random walk (SRRW) which is less likely to transition to nodes that were highly visited in the past, and more likely to transition to seldom visited nodes. For a class of SRRWs parameterized by a positive real α, we prove that the empirical distribution of the process converges almost surely to the target (stationary) distribution of the underlying Markov chain kernel. We then provide a central limit theorem and derive the exact form of the arising asymptotic co-variance matrix, which allows us to show that the SRRW with stronger repellence (larger α) always achieves a smaller asymptotic covariance, in the sense of Loewner ordering of co-variance matrices. Especially for SRRW-driven MCMC algorithms, we show that the decrease in the asymptotic sampling variance is of the order O(1/α), eventually going down to zero. After generalizing these results for a class of weighted empirical measures, we use them as a stepping stone to show that a similar performance ordering can also be obtained for distributed stochastic optimization tasks using token algorithms. More explicitly, by replacing a Markovian token by a SRRW version with the same target distribution, we show that the asymptotic co-variance of the optimization iterates decreases at rate O(1/α^2) - the performance benefit of using SRRW thereby amplified in the stochastic optimization context. Empirical results support our theoretical findings.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Self-Supervised Representation Learning with Meta Comprehensive Regularization

Huijie Guo
Ying Ba
Jie Hu
Lingyu Si
Wenwen Qiang
Lei Shi

Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the shared information among multiple augmented views of samples, while disregarding the non-shared information that may be beneficial for downstream tasks. To address this issue, we introduce a module called CompMod with Meta Comprehensive Regularization (MCR), embedded into existing self-supervised frameworks, to make the learned representations more comprehensive. Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features. Additionally, guided by the constrained extraction of features using maximum entropy coding, the self-supervised learning model learns more comprehensive features on top of learning consistent features. In addition, we provide theoretical support for our proposed method from information theory and causal counterfactual perspective. Experimental results show that our method achieves significant improvement in classification, object detection and semantic segmentation tasks on multiple benchmark datasets.

PDF Details DOI

YNICL Journal 2024 Journal Article

Systematically altered connectome gradient in benign childhood epilepsy with centrotemporal spikes: Potential effect on cognitive function

Jie Hu
Guiqin Chen
Zhen Zeng
Haifeng Ran
Ruoxi Zhang
Qiane Yu
Yuxin Xie
Yulun He

OBJECTIVE: Benign childhood epilepsy with centrotemporal spikes (BECTS) affects brain network hierarchy and cognitive function; however, itremainsunclearhowhierarchical changeaffectscognition in patients with BECTS. A major aim of this study was to examine changes in the macro-network function hierarchy in BECTS and its potential contribution to cognitive function. METHODS: Overall, the study included 50 children with BECTS and 69 healthy controls. Connectome gradient analysis was used to determine the brain network hierarchy of each group. By comparing gradient scores at each voxel level and network between groups, we assessed changes in whole-brain voxel-level and network hierarchy. Functional connectivity was used to detect the functional reorganization of epilepsy caused by these abnormal brain regions based on these aberrant gradients. Lastly, we explored the relationships between the change gradient and functional connectivity values and clinical variables and further predicted the cognitive function associated with BECTS gradient changes. RESULTS: In children with BECTS, the gradient was extended at different network and voxel levels. The gradient scores frontoparietal network was increased in the principal gradient of patients with BECTS. The left precentral gyrus (PCG) and right angular gyrus gradient scores were significantly increased in the principal gradient of children with BECTS. Moreover, in regions of the brain with abnormal principal gradients, functional connectivity was disrupted. The left PCG gradient score of children with BECTS was correlated with the verbal intelligence quotient (VIQ), and the disruption of functional connectivity in brain regions with abnormal principal gradients was closely related to cognitive function. VIQ was significantly predicted by the principal gradient map of patients. SIGNIFICANCE: The results indicate connectome gradient disruption in children with BECTS and its relationship to cognitive function, thereby increasing our understanding of the functional connectome hierarchy and providing potential biomarkers for cognitive function of children with BECTS.

NeurIPS Conference 2024 Conference Paper

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers

Yuchuan Tian
Zhijun Tu
Hanting Chen
Jie Hu
Chao Xu
Yunhe Wang

Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good scalability; but meanwhile, the abandonment of U-Net by DiTs and their following improvements is worth rethinking. To this end, we conduct a simple toy experiment by comparing a U-Net architectured DiT with an isotropic one. It turns out that the U-Net architecture only gain a slight advantage amid the U-Net inductive bias, indicating potential redundancies within the U-Net-style DiT. Inspired by the discovery that U-Net backbone features are low-frequency-dominated, we perform token downsampling on the query-key-value tuple for self-attention and bring further improvements despite a considerable amount of reduction in computation. Based on self-attention with downsampled tokens, we propose a series of U-shaped DiTs (U-DiTs) in the paper and conduct extensive experiments to demonstrate the extraordinary performance of U-DiT models. The proposed U-DiT could outperform DiT-XL with only 1/6 of its computation cost. Codes are available at https: //github. com/YuchuanTian/U-DiT.

PDF Details DOI

EAAI Journal 2024 Journal Article

Weakly supervised semantic segmentation by knowledge graph inference

Jia Zhang
Bo Peng
Xi Wu
Jie Hu

The weakly supervised semantic segmentation (WSSS) training based on image-level labels in convolutional neural network (CNN) is usually divided into two stages: multi-label classification and semantic segmentation. However, most of the existing work focuses on the improvement of the multi-label classification network stage, and little effort has been done to improve the performance of the downstream segmentation networks. In addition, CNN-based local convolution lacks in modeling extensive dependencies among categories. Therefore, in this paper, we propose a graph reasoning method to improve both the upstream and the downstream stages of the multi-label classification network and the semantic segmentation networks. In the multi-label classification network, we utilize external knowledge combined with a graph convolutional network (GCN) to perform global reasoning on the dependencies of each category. In the segmentation network, the Graph Reasoning Mapping Module (GRM) is proposed to explore the knowledge acquired from text corpora and facilitate contextual reasoning in various categories of image regions. The proposed GRM module is able to enhance the feature representation of local convolutions on the high-level semantics of the segmentation network, and adaptively learn the semantic consistency of each sample. We achieve state-of-the-art WSSS performance on PASCAL VOC 2012 and MS-COCO 2014 datasets with only image-level supervision. Extensive experiments on multi-label classification networks and semantic segmentation networks demonstrate the effectiveness of our proposed graph reasoning method on WSSS. Our code is available at: https: //github. com/JIA-ZHANG666/GRM_layer.

NeurIPS Conference 2023 Conference Paper

GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image

Mingjian Zhu
Hanting Chen
Qiangyu Yan
Xudong Huang
Guanyu Lin
Wei Li
Zhijun Tu
Hailin Hu

The extraordinary ability of generative models to generate photographic images has intensified concerns about the spread of disinformation, thereby leading to the demand for detectors capable of distinguishing between AI-generated fake images and real images. However, the lack of large datasets containing images from the most advanced image generators poses an obstacle to the development of such detectors. In this paper, we introduce the GenImage dataset, which has the following advantages: 1) Plenty of Images, including over one million pairs of AI-generated fake images and collected real images. 2) Rich Image Content, encompassing a broad range of image classes. 3) State-of-the-art Generators, synthesizing images with advanced diffusion models and GANs. The aforementioned advantages allow the detectors trained on GenImage to undergo a thorough evaluation and demonstrate strong applicability to diverse images. We conduct a comprehensive analysis of the dataset and propose two tasks for evaluating the detection method in resembling real-world scenarios. The cross-generator image classification task measures the performance of a detector trained on one generator when tested on the others. The degraded image classification task assesses the capability of the detectors in handling degraded images such as low-resolution, blurred, and compressed images. With the GenImage dataset, researchers can effectively expedite the development and evaluation of superior AI-generated image detectors in comparison to prevailing methodologies.

YNIMG Journal 2022 Journal Article

Assessing differential representation of hand movements in multiple domains using stereo-electroencephalographic recordings

Guangye Li
Shize Jiang
Jianjun Meng
Guohong Chai
Zehan Wu
Zhen Fan
Jie Hu
Xinjun Sheng

Invasive brain-computer interfaces (BCI) have made great progress in the reconstruction of fine hand movement parameters for paralyzed patients, where superficial measurement modalities including electrocorticography (ECoG) and micro-array recordings are mostly used. However, these recording techniques typically focus on the signals from the sensorimotor cortex, leaving subcortical regions and other cortical regions related to the movements largely unexplored. As an intracranial recording technique for the presurgical assessments of brain surgery, stereo-encephalography (SEEG) inserts depth electrodes containing multiple contacts into the brain and thus provides the unique opportunity for investigating movement-related neural representation throughout the brain. Although SEEG samples neural signals with high spatial-temporal resolutions, its potential of being used to build BCIs has just been realized recently, and the decoding of SEEG activity related to hand movements has not been comprehensively investigated yet. Here, we systematically evaluated the factors influencing the performance of movement decoding using SEEG signals recorded from 32 human subjects performing a visually-cued hand movement task. Our results suggest that multiple regions in both lateral and depth directions present significant neural selectivity to the task, whereas the sensorimotor area, including both precentral and postcentral cortex, carries the richest discriminative neural information for the decoding. The posterior parietal and prefrontal cortex contribute gradually less, but still rich sources for extracting movement parameters. The insula, temporal and occipital cortex also contains useful task-related information for decoding. Under the cortex layer, white matter presents decodable neural patterns but yields a lower accuracy (42.0 ± 0.8%) than the cortex on average (44.2 ± 0.8%, p<0.01). Notably, collectively using neural signals from multiple task-related areas can significantly enhance the movement decoding performance by 6.9% (p<0.01) on average compared to using a single region. Among the different spectral components of SEEG activity, the high gamma and delta bands offer the most informative features for hand movements reconstruction. Additionally, the phase-amplitude coupling strength between these two frequency ranges correlates positively with the performance of movement decoding. In the temporal domain, maximum decoding accuracy is first reached around 2 s after the onset of movement commands. In sum, this study provides valuable insights for the future motor BCIs design employing both SEEG recordings and other recording modalities.

NeurIPS Conference 2022 Conference Paper

Efficiency Ordering of Stochastic Gradient Descent

Jie Hu
Vishwaraj Doshi
Do-Young Eun

We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i. i. d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense. Specifically, we employ the notion of `efficiency ordering', a well-analyzed tool for comparing the performance of Markov Chain Monte Carlo (MCMC) samplers, for SGD algorithms in the form of Loewner ordering of covariance matrices associated with the scaled iterate errors in the long term. Using this ordering, we show that input sequences that are more efficient for MCMC sampling also lead to smaller covariance of the errors for SGD algorithms in the limit. This also suggests that an arbitrarily weighted MSE of SGD iterates in the limit becomes smaller when driven by more efficient chains. Our finding is of particular interest in applications such as decentralized optimization and swarm learning, where SGD is implemented in a random walk fashion on the underlying communication graph for cost issues and/or data privacy. We demonstrate how certain non-Markovian processes, for which typical mixing-time based non-asymptotic bounds are intractable, can outperform their Markovian counterparts in the sense of efficiency ordering for SGD. We show the utility of our method by applying it to gradient descent with shuffling and mini-batch gradient descent, reaffirming key results from existing literature under a unified framework. Empirically, we also observe efficiency ordering for variants of SGD such as accelerated SGD and Adam, open up the possibility of extending our notion of efficiency ordering to a broader family of stochastic optimization algorithms.

AAAI Conference 2022 Conference Paper

Elastic-Link for Binarized Neural Networks

Jie Hu
Ziheng Wu
Vince Tan
Zhilin Lu
Mengze Zeng
Enhua Wu

Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrained devices. However, in comparison to their full-precision counterparts, BNNs suffer from severe accuracy degradation. Research aiming to reduce this accuracy gap has thus far largely focused on specific network architectures with few or no 1 × 1 convolutional layers, for which standard binarization methods do not work well. Because 1×1 convolutions are common in the design of modern architectures (e. g. GoogleNet, ResNet, DenseNet), it is crucial to develop a method to binarize them effectively for BNNs to be more widely adopted. In this work, we propose an “Elastic- Link” (EL) module to enrich information flow within a BNN by adaptively adding real-valued input features to the subsequent convolutional output features. The proposed EL module is easily implemented and can be used in conjunction with other methods for BNNs. We demonstrate that adding EL to BNNs produces a significant improvement on the challenging large-scale ImageNet dataset. For example, we raise the top-1 accuracy of binarized ResNet26 from 57. 9% to 64. 0%. EL also aids convergence in the training of binarized MobileNet, for which a top-1 accuracy of 56. 4% is achieved. Finally, with the integration of ReActNet, it yields a new state-of-the-art result of 71. 9% top-1 accuracy.

EAAI Journal 2022 Journal Article

Enhancing scene understanding based on deep learning for end-to-end autonomous driving

Jie Hu
Huifang Kong
Qian Zhang
Runwu Liu

Efficient understanding of the environment is a crucial prerequisite for autonomous driving, but explicitly modeling the environment is hard to come true. In contrast, imitation learning, in theory, can arrive at the direct mapping from visual input to driving command, but the inscrutability of scene representation in imitation learning is still a challenging problem. In this paper, we propose to enhance the abstract representation of visual scene from two aspects for better scene understanding, i. e. Visual Guide path and Driving Affordances path. For Visual Guide path, we leverage semantic information as visual priors to learn the intuitive state of the environment, e. g. the spatial semantic occupation of the visual scene. For Driving Affordances path, several driving affordance indicators reflecting the relationship between environment and vehicle behavior are learned as the global guidance to guide the driving system to learn safe and efficient driving policies. With the complementarity of these two paths, a Bilateral Guide Network is designed to realize the complete mapping from visual input to driving command. Our method is evaluated on the CARLA simulator with various scenarios to demonstrate the effectiveness. Besides, comparative analyses are made with some state-of-the-art methods to justify the performance of our method in the aspect of autonomous driving.

AAAI Conference 2022 Conference Paper

ReMoNet: Recurrent Multi-Output Network for Efficient Video Denoising

Liuyu Xiang
Jundong Zhou
Jirui Liu
Zerun Wang
Haidong Huang
Jie Hu
Jungong Han
Yuchen Guo

While deep neural network-based video denoising methods have achieved promising results, it is still hard to deploy them on mobile devices due to their high computational cost and memory demands. This paper aims to develop a lightweight deep video denoising method that is friendly to resource-constrained mobile devices. Inspired by the facts that 1) consecutive video frames usually contain redundant temporal coherency, and 2) neural networks are usually over-parameterized, we propose a multi-input multi-output (MIMO) paradigm to process consecutive video frames within one-forward-pass. The basic idea is concretized to a novel architecture termed Recurrent Multi-output Network (ReMoNet), which consists of recurrent temporal fusion and temporal aggregation blocks and is further reinforced by similarity-based mutual distillation. We conduct extensive experiments on NVIDIA GPU and Qualcomm Snapdragon 888 mobile platform with Gaussian noise and simulated Image- Signal-Processor (ISP) noise. The experimental results show that ReMoNet is both effective and efficient on video denoising. Moreover, we show that ReMoNet is more robust under higher noise level scenarios.

EAAI Journal 2021 Journal Article

Concurrent multi-process graph-based design component synthesis: Framework and algorithm

Bin Chen
Jie Hu
Jin Qi
Weixing Chen

Facing today’s increasingly complex and high-demanded design missions, the abundant and multifarious design components distributed in different disciplines and locations should be fully considered and elaborately synthesized. However, this involves a large amount of data processing workload which heavily restrains the application and development of the traditional graph-based synthesis methods. Therefore, a concurrent multi-process graph-based design component synthesis method is proposed to break the bottleneck. With this method, the heavy workload can be dynamically and efficiently decentralized and shared in a group of processes working simultaneously and concurrently. As an application, a software prototype is presented, and the design component synthesis of a biochemical heating system is completed with it.

YNIMG Journal 2021 Journal Article

Prestimulus dynamics blend with the stimulus in neural variability quenching

Annemarie Wolff
Liang Chen
Shankar Tumati
Mehrshad Golesorkhi
Javier Gomez-Pilar
Jie Hu
Shize Jiang
Ying Mao

Neural responses to the same stimulus show significant variability over trials, with this variability typically reduced (quenched) after a stimulus is presented. This trial-to-trial variability (TTV) has been much studied, however how this neural variability quenching is influenced by the ongoing dynamics of the prestimulus period is unknown. Utilizing a human intracranial stereo-electroencephalography (sEEG) data set, we investigate how prestimulus dynamics, as operationalized by standard deviation (SD), shapes poststimulus activity through trial-to-trial variability (TTV). We first observed greater poststimulus variability quenching in those real trials exhibiting high prestimulus variability as observed in all frequency bands. Next, we found that the relative effect of the stimulus was higher in the later (300-600ms) than the earlier (0-300ms) poststimulus period. Lastly, we replicate our findings in a separate EEG dataset and extend them by finding that trials with high prestimulus variability in the theta and alpha bands had faster reaction times. Together, our results demonstrate that stimulus-related activity, including its variability, is a blend of two factors: 1) the effects of the external stimulus itself, and 2) the effects of the ongoing dynamics spilling over from the prestimulus period - the state at stimulus onset - with the second dwarfing the influence of the first.

ICRA Conference 2021 Conference Paper

Robust Motion Averaging under Maximum Correntropy Criterion

Jihua Zhu
Jie Hu
Huimin Lu 0001
Badong Chen
Zhongyu Li 0002
Yaochen Li

Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem. This method aims to recover global motions from a set of relative motions, where the original method is sensitive to outliers due to using the Frobenius norm error in the optimization. Accordingly, this paper proposes a novel robust motion averaging method based on the maximum correntropy criterion (MCC). Specifically, the correntropy measure is used instead of utilizing Frobenius norm error to improve the robustness of motion averaging against outliers. According to the half-quadratic technique, the correntropy measure based optimization problem can be solved by the alternating minimization procedure, which includes operations of weight assignment and weighted motion averaging. Further, we design a selection strategy of adaptive kernel width to take advantage of correntropy. Experimental results on benchmark data sets illustrate that our method has superior performance on accuracy and robustness for multi-view registration. What’s more, it can be applied to robot mapping.

TCS Journal 2021 Journal Article

The Steiner k-eccentricity on trees

Xingfu Li
Guihai Yu
Sandi Klavžar
Jie Hu
Bo Li

We study the Steiner k-eccentricity on trees, which generalizes the previous one in the paper [On the average Steiner 3-eccentricity of trees, arXiv: 2005. 10319]. We achieve much stronger properties for the Steiner k-ecc tree than that in the previous paper. Based on this, a linear time algorithm is devised to calculate the Steiner k-eccentricity of a vertex in a tree. On the other hand, lower and upper bounds of the average Steiner k-eccentricity index of a tree on order n are established based on a novel technique which is quite different and also much easier to follow than the earlier one.

ICRA Conference 2019 Conference Paper

A Novel Robotic System for Finishing of Freeform Surfaces

Yalun Wen
Jie Hu
Prabhakar R. Pagilla

Surface finishing of freeform surfaces is predominately a manual operation that requires a considerable amount of operator skill; automation of this process has many benefits, including consistent surface quality, preventing hazardous exposure to particulate, etc. A novel robotic surface finishing system, consisting of a robot and an end-effector that includes a force sensor, finishing tool, and proximity laser sensor, is developed in this paper to automate the surface finishing process. The laser sensor is treated as an additional link, and based on it a novel perception system is developed for real-time scanning of the surface that provides the surface profile mesh and the corresponding normal vectors which can be used directly by the robot closed-loop control system for pose tracking. A unique feature of the perception system is that the geometry of the surface profile and normal vectors are all obtained in real-time in the robot base coordinate system, thus eliminating issues such as precise registration of the work piece in the fixture and its location with respect to the robot base coordinates. An impedance-type closed-loop control algorithm is developed for pose tracking. The proposed system and control algorithm are employed to conduct surface finishing experiments on wooden surfaces. A representative sample of the results and measurement images of surface finish are provided to illustrate the capabilities of the robotic surface finishing system. A video of the system in operation is also provided.

NeurIPS Conference 2019 Conference Paper

Information Competing Process for Learning Diversified Representations

Jie Hu
Rongrong Ji
Shengchuan Zhang
Xiaoshuai Sun
Qixiang Ye
Chia-Wen Lin
Qi Tian

Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process (ICP), is proposed in this paper. Aiming to enrich the information carried by feature representations, ICP separates a representation into two parts with different mutual information constraints. The separated parts are forced to accomplish the downstream task independently in a competitive environment which prevents the two parts from learning what each other learned for the downstream task. Such competing parts are then combined synergistically to complete the task. By fusing representation parts learned competitively under different conditions, ICP facilitates obtaining diversified representations which contain rich information. Experiments on image classification and image reconstruction tasks demonstrate the great potential of ICP to learn discriminative and disentangled representations in both supervised and self-supervised learning settings.

NeurIPS Conference 2018 Conference Paper

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

Jie Hu
Li Shen
Samuel Albanie
Gang Sun
Andrea Vedaldi

While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled information to local features. The operators are cheap, both in terms of number of added parameters and computational complexity, and can be integrated directly in existing architectures to improve their performance. Experiments on several datasets show that gather-excite can bring benefits comparable to increasing the depth of a CNN at a fraction of the cost. For example, we find ResNet-50 with gather-excite operators is able to outperform its 101-layer counterpart on ImageNet with no additional learnable parameters. We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.

IJCAI Conference 2018 Conference Paper

Robust Face Sketch Synthesis via Generative Adversarial Fusion of Priors and Parametric Sigmoid

Shengchuan Zhang
Rongrong Ji
Jie Hu
Yue Gao
Chia-Wen Lin

Despite the extensive progress in face sketch synthesis, existing methods are mostly workable under constrained conditions, such as fixed illumination, pose, background and ethnic origin that are hardly to control in real-world scenarios. The key issue lies in the difficulty to use data under fixed conditions to train a model against imaging variations. In this paper, we propose a novel generative adversarial network termed pGAN, which can generate face sketches efficiently using training data under fixed conditions and handle the aforementioned uncontrolled conditions. In pGAN, we embed key photo priors into the process of synthesis and design a parametric sigmoid activation function for compensating illumination variations. Compared to the existing methods, we quantitatively demonstrate that the proposed method can work well on face photos in the wild.

EAAI Journal 2017 Journal Article

A modularized case adaptation method of case-based reasoning in parametric machinery design

Jin Qi
Jie Hu
Yinghong Peng

Case adaptation is fundamentally to successfully applying case-based reasoning (CBR) in parametric machinery design, and support vector machine (SVM)-based adaptation is a promising method for CBR adaptation. But the standard formulation of SVM can only be used as a univariate modeling technique due to its inherent single-output structure, which result in the construction of different SVM-based adaptation engine for each solution element adaptation, and such engines could ignore the effects of the mutual parameter relationships for the adaptation results. This paper focuses on the multivariable adaptation problem in CBR adaptation, and proposes a modularized adaptation method by integrating with multiply relational analysis, case parameter clustering and adaptation engine construction. Firstly, the hidden parameter relationships between problem and solution (P–S), problem and problem (P–P), and solution and solution (S–S) parameters are extracted from old cases, then these parameters are clustered into several parameter clustering (PC) modules in terms of their internal relationships. Finally, multi-output SVM (MSVM) is used to build the adaptation engine for each PC module. This method not only improves the performance of SVM-based adaptation by utilizing the mutual parameter relationships, but also reduces the computational expense of MSVM-based adaptation by partitioning the only one adaptation engine into several sub-engines. Actual design examples are introduced to illustrate the process of modularized adaptation, and the empirical experiments in the different examples are carried out to validate the superiority of our proposed method. Through comparing the adaptation accuracies with those provided by other classical neuro-adaptation methods, the modularized adaptation is proved to be a feasible method for case adaptation.

YNIMG Journal 2017 Journal Article

How do self-interest and other-need interact in the brain to determine altruistic behavior?

Jie Hu
Yue Li
Yunlu Yin
Philip R. Blue
Hongbo Yu
Xiaolin Zhou

Altruistic behavior, i. e. , promoting the welfare of others at a cost to oneself, is subserved by the integration of various social, affective, and economic factors represented in extensive brain regions. However, it is unclear how different regions interact to process/integrate information regarding the helper's interest and recipient's need when deciding whether to behave altruistically. Here we combined an interactive game with functional Magnetic Resonance Imaging (fMRI) and transcranial direct current stimulation (tDCS) to characterize the neural network underlying the processing/integration of self-interest and other-need. At the behavioral level, high self-risk decreased helping behavior and high other-need increased helping behavior. At the neural level, activity in medial prefrontal cortex (MPFC) and right dorsolateral prefrontal cortex (rDLPFC) were positively associated with self-risk levels, and activity in right inferior parietal lobe (rIPL) and rDLPFC were negatively associated with other-need levels. Dynamic causal modeling further suggested that both MPFC and rIPL were extrinsically connected to rDLPFC; high self-risk enhanced the effective connectivity from MPFC to rDLPFC, and the modulatory effect of other-need on the connectivity from rIPL to rDLPFC positively correlated with the modulatory effect of other-need on individuals’ helping rate. Two tDCS experiments provided causal evidence that rDLPFC affects both self-interest and other-need concerns, and rIPL selectively affects the other-need concerns. These findings suggest a crucial role of the MPFC-IPL-DLPFC network during altruistic decision-making, with rDLPFC as a central node for integrating and modulating motives regarding self-interest and other-need.

EAAI Journal 2015 Journal Article

An integrated feature selection and cluster analysis techniques for case-based reasoning

Guo-Niu Zhu
Jie Hu
Jin Qi
Jin Ma
Ying-Hong Peng

Feature selection and case organization are crucial steps in case-based reasoning (CBR), since the retrieval efficiency and accuracy even the success of the CBR system are heavily dependent on their quality. However, inappropriate feature selection and case selection together with ill-structured case organization may not only present a dilemma in case retrieval, but also greatly increase the case base. To obtain an efficient CBR system, selection of proper features and suitable cases with appropriate case organization are very important. This paper proposes a hybrid CBR system by introducing reduction technique in feature selection and cluster analysis in case organization. In this study, a minimal set of features is selected from the problem domain while redundant ones are reduced through neighborhood rough set algorithm. Once feature selection is finished, the growing hierarchical self-organizing map (GHSOM) is taken as a cluster tool to organize those cases so that the initial case base can be divided into some small subsets with hierarchical structure. New case is led into corresponding subset for case retrieval. Experiments on UCI datasets and a practical case in electromotor product design show the effectiveness of the proposed approach. The results indicate that the research techniques can effectively enhance the performance of the CBR system.

EAAI Journal 2015 Journal Article

Incorporating adaptability-related knowledge into support vector machine for case-based design adaptation

Jin Qi
Jie Hu
Yinghong Peng

In case-based design systems, the adaptation operation based on similar cases is a difficult and complex step, and the more adaptable cases usually could make larger contribution for adaptation generation than less ones. Under this ideology, this paper addresses a new case adaptation method which uses support vector machine (SVM) incorporating adaptability-related knowledge provided by the retrieved cases, called adaptability-involving SVM (ASVM). The knowledge of adaptability includes the adaptability characteristic of old cases returned by the adaptability analysis and the guideline that the training data from adaptable case should be given higher weight to build SVM model. So the content of this work presented here consists of two parts. The first one is to explore the adaptable property of old cases by utilizing decision tree technology. The second one is to study the construction of ASVM adaptation model in terms of retrieved cases. We first employ the differences between test and retrieved cases to assemble the adaptation pattern data for ASVM model training. Then the higher adaptability coefficients are given to the training data from more adaptable cases than those from less adaptable cases. We adopt ASVM in actual power transformer design to illustrate its feasibility, and carry out comparison researches with different numbers of retrieved cases in the different data sets to validate its superiority, through comparing the adaptation error results with those provided by other classical methods. Empirical results show that ASVM is feasible and validated for case adaptation.

TCS Journal 2011 Journal Article

Deterministic risk control for cost-effective network connections

Eduardo Álvarez-Miranda
Xujin Chen
Jie Hu
Xiaodong Hu
Alfredo Candia-Véjar

This paper considers the minimum connection problem in networks with uncertain data. In such a network it is assumed that one can establish a link e by paying a cost c e in a given interval [ c e −, c e + ] while taking a risk ( c e + − c e ) / ( c e + − c e − ) of link failure. We develop polynomial time algorithms for minimum cost network connection with paths or spanning trees under risk-sum constraints.

EAAI Journal 2010 Journal Article

Representation of functional micro-knowledge cell (FMKC) for conceptual design

Sheng Li
Jie Hu
Ying-Hong Peng

The conceptual design process of a complex product concerns multidisciplinary design knowledge. This paper presents an approach of consistent knowledge representation for conceptual design. Firstly, the concept of functional micro-knowledge cell (FMKC) is presented, and the knowledge representation approach of FMKC is proposed. In the function layer, the functional ontology is used to provide a rich vocabulary. By constructing the mapping relationships between the function and structure layer, a systematic knowledge representation scheme is obtained. Secondly, the functional knowledge decomposition theory is proposed to unify the resolution of knowledge representation. Finally, the FMKC is applied to a hydraulic cylinder, which demonstrates the possibility in representing the multidisciplinary knowledge for conceptual design with a unified systematic representation scheme. In addition, the FMKC can be used in knowledge fusion and design reuse for our further study.