Arrow Research search

Author name cluster

Yuan Yuan

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.

45 papers
2 author rows

Possible papers

45

EAAI Journal 2026 Journal Article

A zero-shot anomaly detection network with patch-augmented prompts and test-time adaptation

  • Hegui Zhu
  • Chunmeng Zhao
  • Yuan Yuan
  • Meiling Liu

In recent years, pre-trained visual-language models, such as Contrastive Language-Image Pre-training (CLIP), have demonstrated strong generalization capabilities in zero-shot anomaly detection tasks. Due to the scarcity and diversity of anomaly samples, it is impossible to collect enough anomaly samples in many application scenarios, especially in privacy-sensitive scenarios. Moreover, most zero-shot anomaly detection methods with single and fixed text prompts face significant challenges in accurately detecting and localizing anomalies across domains. To address these challenges, this study proposes a zero-shot anomaly detection network, Patch-augmented Prompts and Test-time Adaptation (PPTA-CLIP), which incorporates four key modules to achieve robust anomaly detection performance. First, the modified visual encoder extracts multi-level visual features for subsequent tasks. Second, the patch-augmented text prompts module enhances learnable text prompts by incorporating local visual patch information, thus improving the model’s ability to detect subtle and rare anomaly patterns. Next, the modified text encoder module extracts enhanced text features. Finally, the test-time feature adaptation module refines the learned global features for test inputs, further improving detection performance. After being trained on an auxiliary dataset, the model can be directly used for testing without requiring retraining on other datasets. Extensive experimental results on 14 real-world datasets from industrial and medical fields show that PPTA-CLIP achieves state-of-the-art performance compared to other competitive zero-shot anomaly detection methods.

Details DOI

AAAI Conference 2026 Conference Paper

BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards

  • Yiran Yang
  • Zhaowei Liu
  • Yuan Yuan
  • Yukun Song
  • Xiong Ma
  • Yinghao Song
  • Xiangji Zeng
  • Lu Sun

Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial ads that fuses Chain-of-Thought reasoning with rule-based policy principles and a critic-guided reward. A rule-driven ICoT data-synthesis pipeline jump-starts training by generating structured scene descriptions, reasoning chains and labels, cutting annotation costs. Reinforcement learning then refines the model using a composite reward balancing causal coherence with policy adherence. A multitask architecture models intra-modal manipulations (e.g., exaggerated imagery) and cross-modal mismatches (e.g., subtitle–speech drift), boosting robustness. Experiments on real short-video ads show BLM-Guard surpasses strong baselines in accuracy, consistency and generalization.

PDF Details DOI

AAAI Conference 2026 Conference Paper

ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions

  • Xingwei He
  • Qianru Zhang
  • Pengfei Chen
  • Guanhua Chen
  • Linlin Yu
  • Yuan Yuan
  • Siu-Ming Yiu

Instruction-following is a critical capability of Large Language Models (LLMs). While existing works primarily focus on assessing how well LLMs adhere to user instructions, they often overlook scenarios where instructions contain conflicting constraints—a common occurrence in complex prompts. The behavior of LLMs under such conditions remains under-explored. To bridge this gap, we introduce ConInstruct, a benchmark specifically designed to assess LLMs' ability to detect and resolve conflicts within user instructions. Using this dataset, we evaluate LLMs' conflict detection performance and analyze their conflict resolution behavior. Our experiments reveal two key findings: (1) Most proprietary LLMs exhibit strong conflict detection capabilities, whereas among open-source models, only DeepSeek-R1 demonstrates similarly strong performance. DeepSeek-R1 and Claude-4.5-Sonnet achieve the highest average F1-scores at 91.5% and 87.3%, respectively, ranking first and second overall. (2) Despite their strong conflict detection abilities, LLMs rarely explicitly notify users about the conflicts or request clarification when faced with conflicting constraints. These results underscore a critical shortcoming in current LLMs and highlight an important area for future improvement when designing instruction-following LLMs.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DGTF: Cross-Domain Decentralized Graph Learning with Topology-Aware Knowledge Fusion

  • Ruisheng Zheng
  • Mingyi Li
  • Xiao Zhang
  • Hongjian Shi
  • Yanjie Fu
  • Yuan Yuan
  • Dongxiao Yu

Cross-Domain Decentralized Graph Learning (CD-DGL) is a promising paradigm that enables efficient, privacy-preserving collaboration among multiple parties to unlock the value of cross-domain graph data. However, it faces two fundamental challenges. First, inconsistent label spaces across domains drive local models to learn domain-specific biases, which means domain-invariant topological knowledge extraction beyond label constraints is difficult. Second, existing domain topology shift and heterogeneous model architectures make direct model aggregation infeasible. To address these issues, we first use Extended Persistent Homology (EPH) to reveal and quantify the problem of domain topology shift induced by the cross-domain setting. Building on this insight, we present Decentralized Graph Learning with Topology-Aware Knowledge Fusion (DGTF), a novel framework designed to facilitate positive topological knowledge transfer in CD-DGL. Our framework achieves this by integrating two core strategies: first, a contrastive learning-based approach to extract task-agnostic topological knowledge, and second, a topology-aware, model-independent knowledge fusion method to effectively integrate this topological information. Extensive experiments conducted under various cross-domain and model-heterogeneous settings validate the superiority and effectiveness of our proposed framework.

PDF Details DOI

AAAI Conference 2026 Conference Paper

FreeGaussian: Annotation-free Control of Articulated Objects via 3D Gaussian Splats with Flow Derivatives

  • Qizhi Chen
  • Delin Qu
  • Junli Liu
  • Yiwen Tang
  • Haoming Song
  • Dong Wang
  • Yuan Yuan
  • Bin Zhao

Reconstructing controllable Gaussian splats for articulated objects from monocular video is especially challenging due to its inherently insufficient constraints. Existing methods address this by relying on dense masks and manually defined control signals, limiting their real-world applications. In this paper, we propose an annotation-free method, FreeGaussian, which mathematically disentangles camera egomotion and articulated movements via flow derivatives. By establishing a connection between 2D flows and 3D Gaussian dynamic flow, our method enables optimization and continuity of dynamic Gaussian motions from flow priors without any control signals. Furthermore, we introduce a 3D spherical vector controlling scheme, which represents the state as a 3D Gaussian trajectory, thereby eliminating the need for complex 1D control signal calculations and simplifying controllable Gaussian modeling. Extensive experiments on articulated objects demonstrate the state-of-the-art visual performance and precise, part-aware controllability of our method.

PDF Details DOI

TCS Journal 2026 Journal Article

Open shop scheduling problem with a flexible maintenance period: Revisited

  • Yuan Yuan
  • Xin Han
  • Xingwu Liu
  • Yong Zhou
  • Hao Lu

This paper addresses the two-machine open shop scheduling problem where one flexible maintenance period is imposed on the second machine. The maintenance period must start within a given time window and has a fixed duration. The objective is to minimize the makespan. We demonstrate that a ( 1 + ϵ ) ρ -approximation algorithm can be constructed for the studied problem if there exists a ρ-approximation algorithm for the version with a fixed maintenance period. As a consequence, by applying the polynomial-time approximation scheme (PTAS) for the fixed maintenance period, we derive a PTAS for the problem under consideration, thereby solving an open question in the literature. Furthermore, we propose a 4/3-approximation algorithm with O(n) time complexity, which outperforms the previous 3/2-approximation algorithm presented in the literature.

Details DOI

EAAI Journal 2025 Journal Article

Adaptive neural boundary control for multi-agent manipulators system with uncertainties through cooperative disturbance observers network

  • Zhibo Zhao
  • Yuan Yuan
  • Xiaodong Xu
  • Biao Luo
  • Tingwen Huang

This paper addresses vibration control problem of multi-agent flexible manipulators systems in the presence of simultaneous uncertainty and unknown external disturbance. Particularly, the goal is to suppress vibration of both flexible link and joint angular. In this paper, the dynamic model of the considered flexible manipulator is described by the fourth order partial differential equation. Without control, the system is unstable and vibrate constantly due to initial states, the external unknown disturbances and system uncertainties. To compensate the uncertainty in each agent, the neural networks are employed and novel adaptation laws are developed to update weighting parameters in the neural networks. While for the compensation of the external disturbance a cooperative network of disturbance observers is proposed to enhance the observation reliability. With the resulting estimations of uncertainties and the unknown disturbance, adaptive distributed boundary controllers are derived to suppress vibration in-domain and keep joint angular position to zero. The closed-loop system is proven to be uniform ultimately bounded through Lyapunov stability theory. Numerical simulations result shows that compared with the proportional–derivative control, the proposed method almost reduces all overshoot and steady-state error.

Details DOI

TCS Journal 2025 Journal Article

Adaptive pruning-based Newton's method for distributed learning

  • Shuzhen Chen
  • Yuan Yuan
  • Youming Tao
  • Tianzhu Wang
  • Zhipeng Cai
  • Dongxiao Yu

Newton's method leverages curvature information to boost performance, and thus outperforms first-order methods for distributed learning problems. However, Newton's method is not practical in large-scale and heterogeneous learning environments, due to obstacles such as high computation and communication costs of the Hessian matrix, sub-model diversity, staleness of training, and data heterogeneity. To overcome these obstacles, this paper presents a novel and efficient algorithm named Distributed Adaptive Newton Learning (DANL), which solves the drawbacks of Newton's method by using a simple Hessian initialization and adaptive allocation of training regions. The algorithm exhibits remarkable convergence properties, which are rigorously examined under standard assumptions in stochastic optimization. The theoretical analysis proves that DANL attains a linear convergence rate while efficiently adapting to available resources and keeping high efficiency. Furthermore, DANL shows notable independence from the condition number of the problem and removes the necessity for complex parameter tuning. Experiments demonstrate that DANL achieves linear convergence with efficient communication and strong performance across different datasets.

Details DOI

JBHI Journal 2025 Journal Article

Deep Augmented Metric Learning Network for Prostate Cancer Classification in Ultrasound Images

  • Xu Lu
  • Yanqi Guo
  • Shulian Zhang
  • Yuan Yuan
  • Chun-Chun Wang
  • Zhao Shen
  • Shaopeng Liu

Prostate cancer screening often relies on cost-intensive MRIs and invasive needle biopsies. Transrectal ultrasound imaging, as a more affordable and non-invasive alternative, faces the challenge of high inter-class similarity and intra-class variability between benign and malignant prostate cancers. This complexity requires more stringent differentiation of subtle features for accurate auxiliary diagnosis. In response, we introduce the novel Deep Augmented Metric Learning (DAML) network, specifically tailored for ultrasound-based prostate cancer classification. The DAML network represents a significant innovation in the metric learning space, introducing the Semantic Differences Mining Strategy (SDMS) to effectively discern and represent subtle differences in prostate ultrasound images, thereby enhancing tumor classification accuracy. Additionally, the DAML network strategically addresses class variability and limited sample sizes by combining the Linear Interpolation Augmentation Strategy (LIAS) and Permutation-Aided Reconstruction Loss (PARL). This approach enriches feature representation and introduces variability with straightforward structures, mirroring the efficacy of advanced sample generation techniques. We carried out comprehensive empirical assessments of the DAML model by testing its key components against a range of models, ensuring its effectiveness. Our results demonstrate the enhanced performance of the DAML model, achieving classification accuracies of 0. 857 and 0. 888 for benign and malignant cancers, respectively, underscoring its effectiveness in prostate cancer classification via medical imaging.

Details DOI

NeurIPS Conference 2025 Conference Paper

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

  • Yuan Yuan
  • Chonghua Han
  • Jingtao Ding
  • Guozhen Zhang
  • Depeng Jin
  • Yong Li

The urban environment is characterized by complex spatio-temporal dynamics arising from diverse human activities and interactions. Effectively modeling these dynamics is essential for understanding and optimizing urban systems. In this work, we introduce UrbanDiT, a foundation model for open-world urban spatio-temporal learning that successfully scales up diffusion transformers in this field. UrbanDiT pioneers a unified model that integrates diverse data sources and types while learning universal spatio-temporal patterns across different cities and scenarios. This allows the model to unify both multi-data and multi-task learning, and effectively support a wide range of spatio-temporal applications. Its key innovation lies in the elaborated prompt learning framework, which adaptively generates both data-driven and task-specific prompts, guiding the model to deliver superior performance across various urban applications. UrbanDiT offers three advantages: 1) It unifies diverse data types, such as grid-based and graph-based data, into a sequential format; 2) With task-specific prompts, it supports a wide range of tasks, including bi-directional spatio-temporal prediction, temporal interpolation, spatial extrapolation, and spatio-temporal imputation; and 3) It generalizes effectively to open-world scenarios, with its powerful zero-shot capabilities outperforming nearly all baselines with training data. UrbanDiT sets up a new benchmark for foundation models in the urban spatio-temporal domain. Code and datasets are publicly available at \url{https: //github. com/tsinghua-fib-lab/UrbanDiT}.

PDF Details

EAAI Journal 2025 Journal Article

Dual-domain contrastive learning for three-dimensional multi-parametric magnetic resonance imaging to end-to-end predict kidney cancer subtypes

  • Guoying Ji
  • Lizhi Shao
  • Yihao Zhu
  • Xuwen Li
  • Tianwang Xun
  • Junxian Wu
  • Yabo Zhai
  • Yuan Yuan

Prediction of subtypes is important for clinical decision-making in kidney cancer. Multi-parametric magnetic resonance imaging (mp-MRI) provides a non-invasive way to evaluate tumor characteristics. However, due to the heterogeneity of pixel, modality, and objective representation, the computer-aided diagnosis of subtypes is challenging. In this study, we propose a novel diagnosis framework for kidney cancer subtypes based on mp-MRI, dual-domain contrastive learning network (DCLNet), which has two innovations: (i) the dual-domain contrastive learning scheme based on intra-case consistency and inter-case specificity that mines the correlation and diversity of dual-domain (T1-weighted and T2-weighted) image information, and (ii) the linear diffusion augmentation strategy that enriches training data in three-dimensional image sparse representation and increases the robustness of features. In experiments, a real-world dataset from multiple centers is established for the development and validation of DCLNet. The proposed method yields multiple classification accuracy of 75. 49 % for kidney cancer subtypes. The area under the curve for the aggressive malignant tumor clear cell renal cell carcinoma and the benign tumor angiomyolipoma is 89. 53 % and 88. 95 %, respectively. Significantly, our proposed method demonstrates significant improvement over state-of-the-art methods (p < 0. 01). This study offers a reliable model for non-invasive prediction of kidney cancer subtypes. It also shows potential to overcome multi-source heterogeneity and improve performance in cancer classification. Our code is available at https: //github. com/xiaojidream/DCLNet.

Details DOI

AAAI Conference 2025 Conference Paper

Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model

  • Yujun Li
  • Hongyuan Zhang
  • Yuan Yuan

Graph contrastive learning (GCL) aims to learn representations from unlabeled graph data in a self-supervised manner and has developed rapidly in recent years. However, edge-level contrasts are not well explored by most existing GCL methods. Most studies in GCL only regard edges as auxiliary information while updating node features. One of the primary obstacles of edge-based GCL is the heavy computation burden. To tackle this issue, we propose a model that can efficiently learn edge features for GCL, namely Augmentation-Free Edge Contrastive Learning (AFECL) to achieve edge-edge contrast. AFECL depends on no augmentation consisting of two parts. Firstly, we design a novel edge feature generation method, where edge features are computed by embedding concatenation of their connected nodes. Secondly, an edge contrastive learning scheme is developed, where edges connecting the same nodes are defined as positive pairs, and other edges are defined as negative pairs. Experimental results show that compared with recent state-of-the-art GCL methods or even some supervised GNNs, AFECL achieves SOTA performance on link prediction and semi-supervised node classification of extremely scarce labels.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Enhancing Low-Rank Adaptation with Recoverability-Based Reinforcement Pruning for Object Counting

  • Haojie Guo
  • Junyu Gao
  • Yuan Yuan

Object counting is crucial for understanding the distribution of objects in different scenarios. Recently, many object counting networks have been designed to be more complex to achieve marginal improvements, leading to excessive time spent on model design. With the development of large models (LMs), various visual tasks can be accomplished by transferring pre-trained weights from LMs and fine-tuning them. However, tens of millions of training data make the pre-training parameters of LMs not entirely necessary. Moreover, if unnecessary parameters in the large model are not removed, it may lead to decreased performance on the tasks to be transferred. Motivated by this, this paper proposes an Enhancing low-Rank adaptation with Recoverability-based Reinforcement Pruning (E3RP) method to balance the complexity of large model and the accuracy of counting tasks. Firstly, we design a new reward mechanism based on the feature similarity of large model before and after globally unstructured pruning of specific parameters. Additionally, we propose a Patch Query Flip Attention (PQFA) mechanism to align multi-scale features through bidirectional interaction of features. Finally, the parameters of large model are pruned utilizing the pruning rate autonomously determined by the reinforcement learning network, and the large model is fine-tuned to counting tasks by a simple decoding head. Extensive experiments on four cross-scenario datasets demonstrate that the proposed method can remove redundant network parameters while ensuring network performance, with a maximum reduction of up to 63%.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

GoRA: Gradient-driven Adaptive Low Rank Adaptation

  • Haonan He
  • Peng Ye
  • Yuchen Ren
  • Yuan Yuan
  • Lei Chen

Low-Rank Adaptation (LoRA) is a crucial method for efficiently fine-tuning large language models (LLMs), with its effectiveness influenced by two key factors: rank selection and weight initialization. While numerous LoRA variants have been proposed to improve performance by addressing one of these aspects, they often compromise usability or computational efficiency. In this paper, we analyze and identify the core limitations of existing approaches and propose a novel framework— GoRA ( G radient-driven Adaptive L o w R ank A daptation)—that simultaneously adapts both the rank and initialization strategy within a unified framework. GoRA leverages gradient information during training to dynamically assign optimal ranks and initialize low-rank adapter weights in an adaptive manner. To our knowledge, GoRA is the first method that not only addresses the limitations of prior approaches—which often focus on either rank selection or initialization in isolation—but also unifies both aspects within a single framework, enabling more effective and efficient adaptation. Extensive experiments across various architectures and modalities show that GoRA consistently outperforms existing LoRA-based methods while preserving the efficiency of vanilla LoRA. For example, when fine-tuning Llama3. 1-8B-Base for mathematical reasoning, GoRA achieves a 5. 13-point improvement over standard LoRA and even outperforms full fine-tuning by 2. 05 points under high-rank settings. Code is available at: https: //github. com/hhnqqq/MyTransformers.

PDF Details

TAAS Journal 2025 Journal Article

Multi-Agent Reinforcement Learning based Edge Content Caching for Connected Autonomous Vehicles in IoV

  • Xiaolong Xu
  • Linjie Gu
  • Muhammad Bilal
  • Maqbool Khan
  • Yiping Wen
  • Guoqiang Liu
  • Yuan Yuan

Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data management. The combination of Web3.0 and edge content caching holds promise in providing low-latency data access for CAVs’ real-time applications. Web3.0 enables the reliable pre-migration of frequently requested content from content providers to edge nodes. However, identifying optimal edge node peers for joint content caching and replacement remains challenging due to the dynamic nature of traffic flow in IoV. Addressing these challenges, this article introduces GAMA-Cache, an innovative edge content caching methodology leveraging Graph Attention Networks (GAT) and Multi-Agent Reinforcement Learning (MARL). GAMA-Cache conceptualizes the cooperative edge content caching issue as a constrained Markov decision process. It employs a MARL technique predicated on cooperation effectiveness to discern optimal caching decisions, with GAT augmenting information extracted from adjacent nodes. A distinct collaborator selection mechanism is also developed to streamline communication between agents, filtering out those with minimal correlations in the vector input to the policy network. Experimental results demonstrate that, in terms of service latency and delivery failure, the GAMA-Cache outperforms other state-of-the-art MARL solutions for edge content caching in IoV.

Details DOI

EAAI Journal 2025 Journal Article

Multi-condition pipeline leak diagnosis based on acoustic image fusion and whale-optimized evolutionary convolutional neural network

  • Yuan Yuan
  • Xiwang Cui
  • Xiaojuan Han
  • Yan Gao
  • Fangcheng Lu
  • Xianhong Liu

This study proposes a multi-condition pipeline leak diagnosis method that utilizes pixel-level image fusion and an evolutionary convolutional neural network enhanced by the whale optimization algorithm. Firstly, the traditional one-dimensional leakage time series are transformed into two-dimensional acoustic images, which contain richer information. The signal characteristics, as well as the advantages and disadvantages of different image conversion methods, are compared and analyzed. Secondly, given that a single acoustic image conversion method struggles to achieve effective diagnostics across various working conditions, this study employs two pixel-level image fusion techniques: the principal component transformation method (PCA) and the Intensity-Hue-Saturation (IHS) method, to conduct a comparative study. The results indicate that the diagnostic performance of the fusion methods surpasses that of the unfused acoustic image conversion method, with the IHS method proving to be more suitable for pipeline leakage detection scenarios. In addition, to enhance the accuracy and robustness of pipeline leak detection under varying conditions, a Whale Optimized Evolutionary Convolutional Neural Network model (WOA-ECNN) has been developed for leak diagnosis research. The model was tested under five working conditions (two types of no leakage, 1 mm leakage, 3 mm leakage, and 5 mm leakage). The results demonstrate that the proposed pixel-level fusion method can accurately identify and differentiate between leakage and non-leakage states. Furthermore, multiple performance indicators show superior results compared to the single acoustic image conversion method. In addition, the diagnostic accuracy of the ECNN model, enhanced by whale optimization (WOA-ECNN), is significantly higher than that of the traditional CNN model.

Details DOI

AAAI Conference 2025 Conference Paper

NightHaze: Nighttime Image Dehazing via Self-Prior Learning

  • Beibei Lin
  • Yeying Jin
  • Yan Wending
  • Wei Ye
  • Yuan Yuan
  • Robby T. Tan

Masked autoencoder (MAE) shows that severe augmentation during training produces robust representations for high-level tasks. This paper brings the MAE-like framework to nighttime image enhancement, demonstrating that severe augmentation during training produces strong network priors that are resilient to real-world night haze degradations. We propose a novel nighttime image dehazing method with self-prior learning. Our main novelty lies in the design of severe augmentation, which allows our model to learn robust priors. Unlike MAE that uses masking, we leverage two key challenging factors of nighttime images as augmentation: light effects and noise. During training, we intentionally degrade clear images by blending them with light effects as well as by adding noise, and subsequently restore the clear images. This enables our model to learn clear background priors. By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors. While our self-prior learning is considerably effective in suppressing glow and revealing details of background scenes, in some cases, there are still some undesired artifacts that remain, particularly in the forms of over-suppression. To address these artifacts, we propose a self-refinement module based on the semi-supervised teacher-student framework. Our NightHaze, especially our MAE-like self-prior learning, shows that models trained with severe augmentation effectively improve the visibility of input haze images, approaching the clarity of clear nighttime images. Extensive experiments demonstrate that our NightHaze achieves state-of-the-art performance, outperforming existing nighttime image dehazing methods by a substantial margin of 15.5% for MUSIQ and 23.5% for ClipIQA.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning

  • Xin Yang
  • Wending Yan
  • Yuan Yuan
  • Michael Bi Mi
  • Robby T. Tan

Existing semantic segmentation methods face challenges when processing input images degraded by raindrops on the lens or windshield. Unlike other adverse conditions such as fog and nighttime, which degrade visual quality, raindrops not only impair visual appearances but also introduce misleading occlusion, leading to significant performance drops in current models. The novelty of our approach lies in our two-stage, dual teacher-student framework. We tackle the complex problem of raindrop degradation by dividing it into two distinct challenges: degraded visual appearance and raindrop occlusion. These challenges are then addressed individually in two stages, utilizing two pairs of teacher-student networks. This division enables the networks to develop specialized expertise in handling each aspect of raindrop degradation, enabling their collaboration to achieve superior performance. In the first stage, one teacher-student pair focuses on learning to extract information from visual degraded areas. Building on this, the second teacher-student pair focuses specially on the raindrop occlusion. As such, unlike the existing methods, our approach employs a collaborative approach to decompose and address raindrop-induced degradations. In the second stage, we introduce a mask-based recovery technique to identify and rectify areas that likely contain misleading information, thus further refining the predictions. Additionally, this stage encourages both pairs to expand knowledge by swapping their specialized expertise. Our method achieves a performance of 60.3 mIoU on Rainy WCity and 72.8 mIoU on ACDC Rainy, representing an improvement of +4.4 mIoU and +2.3 mIoU over the existing state-of-the-art methods, respectively.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Where Does It Exist from the Low-Altitude: Spatial Aerial Video Grounding

  • Yang Zhan
  • Yuan Yuan

The task of localizing an object's spatial tube based on language instructions and video, known as spatial video grounding (SVG), has attracted widespread interest. Existing SVG tasks have focused on ego-centric fixed front perspective and simple scenes, which only involved a very limited view and environment. However, UAV-based SVG remains underexplored, which neglects the inherent disparities in drone movement and the complexity of aerial object localization. To facilitate research in this field, we introduce the novel spatial aerial video grounding (SAVG) task. Specifically, we meticulously construct a large-scale benchmark, UAV-SVG, which contains over 2 million frames and offers 216 highly diverse target categories. To address the disparities and challenges posed by complex aerial environments, we propose a new end-to-end transformer architecture, coined SAVG-DETR. The innovations are three-fold. 1) To overcome the computational explosion of self-attention when introducing multi-scale features, our encoder efficiently decouples the multi-modality and multi-scale spatio-temporal modeling into intra-scale multi-modality interaction and cross-scale visual-only fusion. 2) To enhance small object grounding ability, we propose the language modulation module to integrate multi-scale information into language features and the multi-level progressive spatial decoder to decode from high to low level. The decoding stage for the lower-level vision-language features is gradually increased. 3) To improve the prediction consistency across frames, we design the decoding paradigm based on offset generation. At each decoding stage, we utilize reference anchors to constrict the grounding region, use context-rich object queries to predict offsets, and update reference anchors for the next stage. From coarse to fine, our SAVG-DETR gradually bridges the modality gap and iteratively refines reference anchors of the referred object, eventually grounding the spatial tube. Extensive experiments demonstrate that our SAVG-DETR significantly outperforms existing state-of-the-art methods. The dataset and code will be available at here.

PDF Details

ICLR Conference 2024 Conference Paper

Continuous Invariance Learning

  • Lin Yong
  • Fan Zhou 0012
  • Lu Tan
  • Lintao Ma
  • Jianmeng Liu
  • Yansu He
  • Yuan Yuan
  • Yu Liu 0071

Invariance learning methods aim to learn invariant features in the hope that they generalize under distributional shift. Although many tasks are naturally characterized by continuous domains, current invariance learning techniques generally assume categorically indexed domains. For example, auto-scaling in cloud computing often needs a CPU utilization prediction model that generalizes across different times (e.g., time of a day and date of a year), where `time' is a continuous domain index. In this paper, we start by theoretically showing that existing invariance learning methods can fail for continuous domain problems. Specifically, the naive solution of splitting continuous domains into discrete ones ignores the underlying relationship among domains, and therefore potentially leads to suboptimal performance. To address this challenge, we then propose Continuous Invariance Learning (CIL), which extracts invariant features across continuously indexed domains. CIL is a novel adversarial procedure which measures and controls the conditional independence between the labels and continuous domain indices given the extracted features. Our theoretical analysis demonstrates that CIL learns features that satisfy the invariant constraint with infinite samples. Empirical results on both synthetic and real-world datasets (including data collected from production systems) show that CIL consistently outperforms strong baselines among all the tasks.

Details

TIST Journal 2024 Journal Article

Demand-driven Urban Facility Visit Prediction

  • Yunke Zhang
  • Tong Li
  • Yuan Yuan
  • Fengli Xu
  • Fan Yang
  • Funing Sun
  • Yong Li

Predicting citizens’ visiting behaviors to urban facilities is instrumental for city governors and planners to detect inequalities in urban opportunities and optimize the distribution of facilities and resources. Previous works predict facility visits simply using observed visit behavior, yet citizens’ intrinsic demands for facilities are not characterized explicitly, causing potential incorrect learned relations in the prediction results. In this article, to make up for this deficiency, we present a demand-driven urban facility visit prediction method that decomposes citizens’ visits to facilities into their unobservable demands and their capability to fulfill them. Demands are expressed as the function of regional demographic attributes by a neural network, and the fulfillment capability is determined by the urban region’s spatial accessibility to facilities. Extensive evaluations of datasets of three large cities confirm the efficiency and rationality of our model. Our method outperforms the best state-of-the-art model by 8.28% on average in facility visit prediction tasks. Further analyses demonstrate the reasonableness of recovered facility demands and their relationship with citizen demographics. For instance, senior citizens tend to have higher medical demands but lower shopping demands. Meanwhile, estimated capabilities and accessibilities provide deeper insights into the decaying accessibility with respect to spatial distance and facilities’ diverse functions in the urban environment. Our findings shed light on demand-driven urban data mining and demand-based urban facility planning.

Details DOI

AAAI Conference 2024 Conference Paper

DeS3: Adaptive Attention-Driven Self and Soft Shadow Removal Using ViT Similarity

  • Yeying Jin
  • Wei Ye
  • Wenhan Yang
  • Yuan Yuan
  • Robby T. Tan

Removing soft and self shadows that lack clear boundaries from a single image is still challenging. Self shadows are shadows that are cast on the object itself. Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows. In this paper, we present DeS3, a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our novel ViT similarity loss utilizes features extracted from a pre-trained Vision Transformer. This loss helps guide the reverse sampling towards recovering scene structures. Our adaptive attention is able to differentiate shadow regions from the underlying objects, as well as shadow regions from the object casting the shadow. This capability enables DeS3 to better recover the structures of objects even when they are partially occluded by shadows. Different from existing methods that rely on constraints during the training phase, we incorporate the ViT similarity during the sampling stage. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets, removing hard, soft, and self shadows robustly. Specifically, our method outperforms the SOTA method by 16% of the RMSE of the whole image on the LRSS dataset.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning

  • Xin Yang
  • Yan Wending
  • Michael B. Mi
  • Yuan Yuan
  • Robby T. Tan

Adverse weather conditions can significantly degrade the video frames, causing existing video semantic segmentation methods to produce erroneous predictions. In this work, we target adverse weather conditions and introduce an end-to-end domain adaptation strategy that leverages a fusion block, temporal-spatial teacher-student learning, and a temporal weather degradation augmentation approach. The fusion block integrates temporal information from adjacent frames at the feature level, trained end-to-end, eliminating the need for pretrained optical flow, distinguishing our method from existing approaches. Our teacher-student approach involves two teachers: one focuses on exploring temporal information from adjacent frames, and the other harnesses spatial information from the current frame. Finally, we apply temporal weather degradation augmentation to consecutive frames to more accurately represent adverse weather degradations. Our method achieves a performance of 25. 4 and 33. 0 mIoU on the adaptation from VIPER and Synthia to MVSS, respectively, representing an improvement of 4. 3 and 5. 8 mIoU over the existing state-of-the-art method.

PDF Details DOI

TCS Journal 2024 Journal Article

Flow shop scheduling problems with transportation constraints revisited

  • Yan Lan
  • Yuan Yuan
  • Yinling Wang
  • Xin Han
  • Yong Zhou

This paper investigates two flow shop scheduling problems with two machines A and B, and a single transporter V. In the first problem, the transporter V is located at machine A initially, each job has to be processed first on A, then transported to B for further processing. While in the second problem, the transporter V is located at machine B initially, each job needs to be processed first on A, then on B, finally transported to the destination. In both problems, the transporter V can carry up to c (where c is a constant and c ≥ 1 ) jobs at a time and the objective is to minimize the makespan. For the former problem, the best approximation algorithm guarantees a worst-case ratio bound of ( 5 3 + ε ), while for the latter one, the best approximation algorithm provides a worst-case ratio bound of 2. For each problem, we design a polynomial-time approximation scheme (PTAS).

Details DOI

TIST Journal 2024 Journal Article

Generating Daily Activities with Need Dynamics

  • Yuan Yuan
  • Jingtao Ding
  • Huandong Wang
  • Depeng Jin

Daily activity data recording individuals’ various activities in daily life are widely used in many applications such as activity scheduling, activity recommendation, and policymaking. Though with high value, its accessibility is limited due to high collection costs and potential privacy issues. Therefore, simulating human activities to produce massive high-quality data is of great importance. However, existing solutions, including rule-based methods with simplified behavior assumptions and data-driven methods directly fitting real-world data, both cannot fully qualify for matching reality. In this article, motivated by the classic psychological theory, Maslow’s need theory describing human motivation, we propose a knowledge-driven simulation framework based on generative adversarial imitation learning. Our core idea is to model the evolution of human needs as the underlying mechanism that drives activity generation in the simulation model. Specifically, a hierarchical model structure that disentangles different need levels and the use of neural stochastic differential equations successfully capture the piecewise-continuous characteristics of need dynamics. Extensive experiments demonstrate that our framework outperforms the state-of-the-art baselines regarding data fidelity and utility. We also present the insightful interpretability of the need modeling. Moreover, privacy preservation evaluations validate that the generated data does not leak individual privacy. The code is available at https://github.com/tsinghua-fib-lab/Activity-Simulation-SAND.

Details DOI

AAAI Conference 2024 Conference Paper

HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping

  • Xin Zhang
  • Jinheng Xie
  • Yuan Yuan
  • Michael Bi Mi
  • Robby T. Tan

Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. However, their scopes only build upon patch-level features within an image, neglecting region/image-level and cross-image relationships at a broader scale. Moreover, these methods cannot differentiate various semantics from multiple instances. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing (HEAP). Specifically, a novel lightweight head with cross-attention mechanism is designed to adaptively group intra-image patches into semantically coherent regions based on correlation among self-supervised features. Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images. Also, an image-level contrastive loss is present to push foreground and background representations apart, with which foreground objects and background are accordingly discovered. HEAP facilitates efficient hierarchical image decomposition, which contributes to more accurate object discovery while also enabling differentiation among objects of various classes. Extensive experimental results on semantic segmentation retrieval, unsupervised object discovery, and saliency detection tasks demonstrate that HEAP achieves state-of-the-art performance.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Improving Factual Error Correction by Learning to Inject Factual Errors

  • Xingwei He
  • Qianru Zhang
  • A-Long Jin
  • Jun Ma
  • Yuan Yuan
  • Siu Ming Yiu

Factual error correction (FEC) aims to revise factual errors in false claims with minimal editing, making them faithful to the provided evidence. This task is crucial for alleviating the hallucination problem encountered by large language models. Given the lack of paired data (i.e., false claims and their corresponding correct claims), existing methods typically adopt the ‘mask-then-correct’ paradigm. This paradigm relies solely on unpaired false claims and correct claims, thus being referred to as distantly supervised methods. These methods require a masker to explicitly identify factual errors within false claims before revising with a corrector. However, the absence of paired data to train the masker makes accurately pinpointing factual errors within claims challenging. To mitigate this, we propose to improve FEC by Learning to Inject Factual Errors (LIFE), a three-step distantly supervised method: ‘mask-corrupt-correct’. Specifically, we first train a corruptor using the ‘mask-then-corrupt’ procedure, allowing it to deliberately introduce factual errors into correct text. The corruptor is then applied to correct claims, generating a substantial amount of paired data. After that, we filter out low-quality data, and use the remaining data to train a corrector. Notably, our corrector does not require a masker, thus circumventing the bottleneck associated with explicit factual error identification. Our experiments on a public dataset verify the effectiveness of LIFE in two key aspects: Firstly, it outperforms the previous best-performing distantly supervised method by a notable margin of 10.59 points in SARI Final (19.3% improvement). Secondly, even compared to ChatGPT prompted with in-context examples, LIFE achieves a superiority of 7.16 points in SARI Final.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

MetaISP: Efficient RAW-to-sRGB Mappings with Merely 1M Parameters

  • Zigeng Chen
  • Chaowei Liu
  • Yuan Yuan
  • Michael Bi Mi
  • Xinchao Wang

State-of-the-art deep ISP models alleviate the dilemma of limited generalization capabilities across heterogeneous inputs by increasing the size and complexity of the network, which inevitably leads to considerable growth in parameter counts and FLOPs. To address this challenge, this paper presents MetaISP - a streamlined model that achieves superior reconstruction quality by adaptively modulating its parameters and architecture in response to diverse inputs. Our rationale revolves around obtaining corresponding spatial and channel-wise correction matrices for various inputs within distinct feature spaces, which assists in assigning optimal attention. This is achieved by predicting dynamic weights for each input image and combining these weights with multiple learnable basis matrices to construct the correction matrices. The proposed MetaISP makes it possible to obtain best performance while being computationally efficient. SOTA results are achieved on two large-scale datasets, e. g. 23. 80dB PSNR on ZRR, exceeding the previous SOTA 0. 19dB with only 9. 2% of its parameter count and 10. 6% of its FLOPs; 25. 06dB PSNR on MAI21, exceeding the previous SOTA 0. 17dB with only 0. 9% of its parameter count and 2. 7% of its FLOPs.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Mono3DVG: 3D Visual Grounding in Monocular Images

  • Yang Zhan
  • Yuan Yuan
  • Zhitong Xiong

We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be released.

PDF Details DOI

AAAI Conference 2024 Conference Paper

NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction

  • Beibei Lin
  • Yeying Jin
  • Wending Yan
  • Wei Ye
  • Yuan Yuan
  • Shunli Zhang
  • Robby T. Tan

Existing deep-learning-based methods for nighttime video deraining rely on synthetic data due to the absence of real-world paired data. However, the intricacies of the real world, particularly with the presence of light effects and low-light regions affected by noise, create significant domain gaps, hampering synthetic-trained models in removing rain streaks properly and leading to over-saturation and color shifts. Motivated by this, we introduce NightRain, a novel nighttime video deraining method with adaptive-rain-removal and adaptive-correction. Our adaptive-rain-removal uses unlabeled rain videos to enable our model to derain real-world rain videos, particularly in regions affected by complex light effects. The idea is to allow our model to obtain rain-free regions based on the confidence scores. Once rain-free regions and the corresponding regions from our input are obtained, we can have region-based paired real data. These paired data are used to train our model using a teacher-student framework, allowing the model to iteratively learn from less challenging regions to more challenging regions. Our adaptive-correction aims to rectify errors in our model's predictions, such as over-saturation and color shifts. The idea is to learn from clear night input training videos based on the differences or distance between those input videos and their corresponding predictions. Our model learns from these differences, compelling our model to correct the errors. From extensive experiments, our method demonstrates state-of-the-art performance. It achieves a PSNR of 26.73dB, surpassing existing nighttime video deraining methods by a substantial margin of 13.7%.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention

  • Xin Yang
  • Wending Yan
  • Yuan Yuan
  • Michael Bi Mi
  • Robby T. Tan

Semantic segmentation's performance is often compromised when applied to unlabeled adverse weather conditions. Unsupervised domain adaptation is a potential approach to enhancing the model's adaptability and robustness to adverse weather. However, existing methods encounter difficulties when sequentially adapting the model to multiple unlabeled adverse weather conditions. They struggle to acquire new knowledge while also retaining previously learned knowledge. To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudo-label blending, and weather composition replay. Our adaptive knowledge acquisition enables the model to avoid learning from extreme images that could potentially cause the model to forget. In our approach of blending pseudo-labels, we not only utilize the current model but also integrate the previously learned model into the ongoing learning process. This collaboration between the current teacher and the previous model enhances the robustness of the pseudo-labels for the current target. Our weather composition replay mechanism allows the model to continuously refine its previously learned weather information while simultaneously learning from the new target domain. Our method consistently outperforms the state-of-the-art methods, and obtains the best performance with averaged mIoU (%) of 65.7 and the lowest forgetting (%) of 3.6 against 60.1 and 11.3, on the ACDC datsets for a four-target continual multi-target domain adaptation.

PDF Details DOI

TIST Journal 2023 Journal Article

Discovering Causes of Traffic Congestion via Deep Transfer Clustering

  • Mudan Wang
  • Yuan Yuan
  • Huan Yan
  • HONGJIE SUI
  • Fan Zuo
  • Yue Liu
  • Yong Li
  • Depeng Jin

Traffic congestion incurs long delay in travel time, which seriously affects our daily travel experiences. Exploring why traffic congestion occurs is significantly important to effectively address the problem of traffic congestion and improve user experience. Traditional approaches to mine the congestion causes depend on human efforts, which is time consuming and cost-intensive. Hence, we aim at discovering the known and unknown causes of traffic congestion in a systematic way. However, to achieve it, there are three challenges: (1) traffic congestion is affected by several factors with complex spatio-temporal relations; (2) there are a few samples of congestion data with known causes due to the limitation of human label; (3) more unknown congestion causes are unexplored since several factors contribute to traffic congestion. To address above challenges, we design a congestion cause discovery system consisting of two modules: (1) congestion feature extraction module, which extracts the important features distinguishing between different causes of congestion; and (2) congestion cause discovery module, which designs a deep semi-supervised learning based framework to discover the causes of traffic congestion with limited labeled data. Specifically, in pre-training stage, it first leverages a few labeled data as prior knowledge to pre-train the model. Then, in clustering stage, we propose two different clustering methods to discover the congestion causes. For the first clustering method, we extend the classic deep embedded clustering model to produce clusters via soft assignment. For the second one, we iteratively use k -means to group the latent features extracted from the pre-trained model, and use the cluster results as pseudo-labels to fine-tune the network. Extensive experiments show that the performance of our methods is superior to the state-of-the-art baselines, which demonstrates the effectiveness of the proposed cause discovery system. Additionally, our system is deployed and used in the practical production environment at Amap.

Details DOI

AIJ Journal 2023 Journal Article

Iterative genetic improvement: Scaling stochastic program synthesis

  • Yuan Yuan
  • Wolfgang Banzhaf

Program synthesis aims to automatically find programs from an underlying programming language that satisfy a given specification. While this has the potential to revolutionize computing, how to search over the vast space of programs efficiently is an unsolved challenge in program synthesis. In cases where large programs are required for a solution, it is generally believed that stochastic search has advantages over other classes of search techniques. Unfortunately, existing stochastic program synthesizers do not meet this expectation very well, suffering from the scalability issue. To overcome this problem, we propose a new framework for stochastic program synthesis, called iterative genetic improvement. The key idea is to apply genetic improvement to improve a current reference program, and then iteratively replace the reference program by the best program found. Compared to traditional stochastic synthesis approaches, iterative genetic improvement can build up the complexity of programs incrementally in a more robust way. We evaluate the approach on two program synthesis domains: list manipulation and string transformation, along with a number of general program synthesis problems. Our empirical results indicate that this method has considerable advantages over several representative stochastic program synthesizer techniques, both in terms of scalability and of solution quality.

Details DOI

IJCAI Conference 2023 Conference Paper

Multi-level Graph Contrastive Prototypical Clustering

  • Yuchao Zhang
  • Yuan Yuan
  • Qi Wang

Recently, graph neural networks (GNNs) have drawn a surge of investigations in deep graph clustering. Nevertheless, existing approaches predominantly are inclined to semantic-agnostic since GNNs exhibit inherent limitations in capturing global underlying semantic structures. Meanwhile, multiple objectives are imposed within one latent space, whereas representations from different granularities may presumably conflict with each other, yielding severe performance degradation for clustering. To this end, we propose a novel Multi-Level Graph Contrastive Prototypical Clustering (MLG-CPC) framework for end-to-end clustering. Specifically, a Prototype Discrimination (ProDisc) objective function is proposed to explicitly capture semantic information via cluster assignments. Moreover, to alleviate the issue of objectives conflict, we introduce to perceive representations of different granularities within individual feature-, prototypical-, and cluster-level spaces by the feature decorrelation, prototype contrast, and cluster space consistency respectively. Extensive experiments on four benchmarks demonstrate the superiority of the proposed MLG-CPC against the state-of-the-art graph clustering approaches.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

EMGC²F: Efficient Multi-view Graph Clustering with Comprehensive Fusion

  • Danyang Wu
  • Jitao Lu
  • Feiping Nie
  • Rong Wang
  • Yuan Yuan

This paper proposes an Efficient Multi-view Graph Clustering with Comprehensive Fusion (EMGC²F) model and a corresponding efficient optimization algorithm to address multi-view graph clustering tasks effectively and efficiently. Compared to existing works, our proposals have the following highlights: 1) EMGC²F directly finds a consistent cluster indicator matrix with a Super Nodes Similarity Minimization module from multiple views, which avoids time-consuming spectral decomposition in previous works. 2) EMGC²F comprehensively mines information from multiple views. More formally, it captures the consistency of multiple views via a Cross-view Nearest Neighbors Voting (CN²V) mechanism, meanwhile capturing the importance of multiple views via an adaptive weighted-learning mechanism. 3) EMGC²F is a parameter-free model and the time complexity of the proposed algorithm is far less than existing works, demonstrating the practicability. Empirical results on several benchmark datasets demonstrate that our proposals outperform SOTA competitors both in effectiveness and efficiency.

PDF Details DOI

JBHI Journal 2022 Journal Article

Improving Breast Tumor Segmentation in PET via Attentive Transformation Based Normalization

  • Xiaoya Qiao
  • Chunjuan Jiang
  • Panli Li
  • Yuan Yuan
  • Qinglong Zeng
  • Lei Bi
  • Shaoli Song
  • Jinman Kim

Positron Emission Tomography (PET) has become a preferred imaging modality for cancer diagnosis, radiotherapy planning, and treatment responses monitoring. Accurate and automatic tumor segmentation is the fundamental requirement for these clinical applications. Deep convolutional neural networks have become the state-of-the-art in PET tumor segmentation. The normalization process is one of the key components for accelerating network training and improving the performance of the network. However, existing normalization methods either introduce batch noise into the instance PET image by calculating statistics on batch level or introduce background noise into every single pixel by sharing the same learnable parameters spatially. In this paper, we proposed an attentive transformation (AT)-based normalization method for PET tumor segmentation. We exploit the distinguishability of breast tumor in PET images and dynamically generate dedicated and pixel-dependent learnable parameters in normalization via the transformation on a combination of channel-wise and spatial-wise attentive responses. The attentive learnable parameters allow to re-calibrate features pixel-by-pixel to focus on the high-uptake area while attenuating the background noise of PET images. Our experimental results on two real clinical datasets show that the AT-based normalization method improves breast tumor segmentation performance when compared with the existing normalization methods.

Details DOI

IJCAI Conference 2022 Conference Paper

Intelligence in Strategic Games (Extended Abstract)

  • Pavel Naumov
  • Yuan Yuan

If an agent, or a coalition of agents, has a strategy, knows that she has a strategy, and knows what the strategy is, then she has a know-how strategy. Several modal logics of coalition power for know-how strategies have been studied before. The contribution of the article is three-fold. First, it proposes a new class of know-how strategies that depend on the intelligence information about the opponents' actions. Second, it shows that the coalition power modality for the proposed new class of strategies cannot be expressed through the standard know-how modality. Third, it gives a sound and complete logical system that describes the interplay between the coalition power modality with intelligence and the distributed knowledge modality in games with imperfect information.

PDF Details DOI

JAIR Journal 2021 Journal Article

Intelligence in Strategic Games

  • Pavel Naumov
  • Yuan Yuan

If an agent, or a coalition of agents, has a strategy, knows that she has a strategy, and knows what the strategy is, then she has a know-how strategy. Several modal logics of coalition power for know-how strategies have been studied before. The contribution of the article is three-fold. First, it proposes a new class of know-how strategies that depend on the intelligence information about the opponents’ actions. Second, it shows that the coalition power modality for the proposed new class of strategies cannot be expressed through the standard know-how modality. Third, it gives a sound and complete logical system that describes the interplay between the coalition power modality with intelligence and the distributed knowledge modality in games with imperfect information.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Subgroup-based Rank-1 Lattice Quasi-Monte Carlo

  • Yueming LYU
  • Yuan Yuan
  • Ivor Tsang

Quasi-Monte Carlo (QMC) is an essential tool for integral approximation, Bayesian inference, and sampling for simulation in science, etc. In the QMC area, the rank-1 lattice is important due to its simple operation, and nice property for point set construction. However, the construction of the generating vector of the rank-1 lattice is usually time-consuming through an exhaustive computer search. To address this issue, we propose a simple closed-form rank-1 lattice construction method based on group theory. Our method reduces the number of distinct pairwise distance values to generate a more regular lattice. We theoretically prove a lower and an upper bound of the minimum pairwise distance of any non-degenerate rank-1 lattice. Empirically, our methods can generate near-optimal rank-1 lattice compared with Korobov exhaustive search regarding the $l_1$-norm and $l_2$-norm minimum distance. Moreover, experimental results show that our method achieves superior approximation performance on the benchmark integration test problems and the kernel approximation problems.

PDF Details

NeurIPS Conference 2020 Conference Paper

Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning

  • Tao Han
  • Junyu Gao
  • Yuan Yuan
  • Qi Wang

Unlabeled data learning has attracted considerable attention recently. However, it is still elusive to extract the expected high-level semantic feature with mere unsupervised learning. In the meantime, semi-supervised learning (SSL) demonstrates a promising future in leveraging few samples. In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating. Specifically, unsupervised semantic aggregation based on Triplet Mutual Information (T-MI) loss is explored to generate semantic labels for unlabeled data. Then the semantic labels are aligned to the actual class by the supervision of labeled data. Furthermore, a feature pool that stores the labeled samples is dynamically updated to assign proxy labels for unlabeled data, which are used as targets for cross-entropy minimization. Extensive experiments and analysis across four standard semi-supervised learning benchmarks validate that USADTM achieves top performance (e. g. , 90. 46% accuracy on CIFAR-10 with 40 labels and 95. 20% accuracy with 250 labels). The code is released at https: //github. com/taohan10200/USADTM.

PDF Details

AAAI Conference 2019 Conference Paper

ACM: Adaptive Cross-Modal Graph Convolutional Neural Networks for RGB-D Scene Recognition

  • Yuan Yuan
  • Zhitong Xiong
  • Qi Wang

RGB image classification has achieved significant performance improvement with the resurge of deep convolutional neural networks. However, mono-modal deep models for RGB image still have several limitations when applied to RGB-D scene recognition. 1) Images for scene classification usually contain more than one typical object with flexible spatial distribution, so the object-level local features should also be considered in addition to global scene representation. 2) Multi-modal features in RGB-D scene classification are still under-utilized. Simply combining these modal-specific features suffers from the semantic gaps between different modalities. 3) Most existing methods neglect the complex relationships among multiple modality features. Considering these limitations, this paper proposes an adaptive crossmodal (ACM) feature learning framework based on graph convolutional neural networks for RGB-D scene recognition. In order to make better use of the modal-specific cues, this approach mines the intra-modality relationships among the selected local features from one modality. To leverage the multi-modal knowledge more effectively, the proposed approach models the inter-modality relationships between two modalities through the cross-modal graph (CMG). We evaluate the proposed method on two public RGB-D scene classification datasets: SUN-RGBD and NYUD V2, and the proposed method achieves state-of-the-art performance.

PDF Details

AAAI Conference 2019 Conference Paper

Memory-Augmented Temporal Dynamic Learning for Action Recognition

  • Yuan Yuan
  • Dong Wang
  • Qi Wang

Human actions captured in video sequences contain two crucial factors for action recognition, i. e. , visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted in most existing successful methods for recognizing actions. However, CNN based methods are limited in modeling long-term motion dynamics. RNNs are able to learn temporal motion dynamics but lack effective ways to tackle unsteady dynamics in long-duration motion. In this work, we propose a memory-augmented temporal dynamic learning network, which learns to write the most evident information into an external memory module and ignore irrelevant ones. In particular, we present a differential memory controller to make a discrete decision on whether the external memory module should be updated with current feature. The discrete memory controller takes in the memory history, context embedding and current feature as inputs and controls information flow into the external memory module. Additionally, we train this discrete memory controller using straight-through estimator. We evaluate this end-to-end system on benchmark datasets (UCF101 and HMDB51) of human action recognition. The experimental results show consistent improvements on both datasets over prior works and our baselines.

PDF Details

IJCAI Conference 2017 Conference Paper

Convolutional 2D LDA for Nonlinear Dimensionality Reduction

  • Qi Wang
  • Zequn Qin
  • Feiping Nie
  • Yuan Yuan

Representing high-volume and high-order data is an essential problem, especially in machine learning field. Although existing two-dimensional (2D) discriminant analysis achieves promising performance, the single and linear projection features make it difficult to analyze more complex data. In this paper, we propose a novel convolutional two-dimensional linear discriminant analysis (2D LDA) method for data representation. In order to deal with nonlinear data, a specially designed Convolutional Neural Networks (CNN) is presented, which can be proved having the equivalent objective function with common 2D LDA. In this way, the discriminant ability can benefit from not only the nonlinearity of Convolutional Neural Networks, but also the powerful learning process. Experiment results on several datasets show that the proposed method performs better than other state-of-the-art methods in terms of classification accuracy.

PDF Details

IJCAI Conference 2017 Conference Paper

JM-Net and Cluster-SVM for Aerial Scene Classification

  • Xiaoqiang Lu
  • Yuan Yuan
  • Jie Fang

Aerial scene classification, which is a fundamental problem for remote sensing imagery, can automatically label an aerial image with a specific semantic category. Although deep learning has achieved competitive performance for aerial scene classification, training the conventional neural networks with aerial datasets will easily stick in overtting and local minimum. Because the aerial datasets only contain a few hundreds or thousands images, meanwhile the conventional networks usually contain millions of parameters to be trained. To address the problem, a novel convolutional neural network named JM-Net is proposed in this paper, which has different size of convolution kernels in same layer and ignores the fully convolytion layer, so it has fewer parameters and can be trained well on aerial datasets. Additionally, Cluster-SVM, a strategy to improve the accuracy and speed up the classification is used in the specific task. Finally, our method suparssed the state-of-art result on the challenging AID dataset while cost shorter time and used smaller storage space.

PDF Details

IROS Conference 2008 Conference Paper

Forward Passageway based collision-free target tracking for mobile robot with local sensing

  • Yuan Yuan
  • Zhiqiang Cao 0002
  • Zeng-Guang Hou
  • Min Tan 0001

This paper proposes a new forward passageway (FP) based real-time collision-free target tracking approach for a mobile robot with local sensing. After the position of the target is estimated and localized in robot coordinate system through the combination of vision system and encoder, the sonar information and the target position are converted to a uniform environment model framework called decision-making space. Based on the space, a FP based decision-making is given to endow the robot with the ability to avoid possible obstacles and track the target in unknown environments. Experiment results show the validity of the proposed approach.

Details
v2026.09.13