Author name cluster

Xiawu Zheng

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.

35 papers

2 author rows

AAAI Conference 2026 Conference Paper

Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning

Liqin Luo
Guangyao Chen
Xiawu Zheng
Yongxing Dai
Yixiong Zou
Yonghong Tian

Visual grounding, the task of linking textual queries to specific regions within images, plays a pivotal role in vision-language integration. Existing methods typically rely on extensive task-specific annotations and fine-tuning, limiting their ability to generalize effectively to novel or out-of-distribution scenarios. To address these limitations, we introduce GroundingAgent, a novel agentic visual grounding framework that operates without any task-specific fine-tuning. GroundingAgent employs a structured, iterative reasoning mechanism that integrates pretrained open-vocabulary object detectors, multimodal large language models (MLLMs), and large language models (LLMs) to progressively refine candidate regions through joint semantic and spatial analyses. Remarkably, GroundingAgent achieves an average zero-shot grounding accuracy of 65.1% on widely-used benchmarks (RefCOCO, RefCOCO+, RefCOCOg), entirely without fine-tuning. Furthermore, by substituting MLLM-generated captions with the original query texts, the accuracy at the selection stage alone reaches approximately 90%, closely matching supervised performance and underscoring the critical role of LLM reasoning capabilities. GroundingAgent also offers strong interpretability, transparently illustrating each reasoning step, thus providing clear insights into its decision-making process.

PDF Details DOI

AAAI Conference 2026 Conference Paper

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

Yongdong Luo
Wang Chen
Weizhong Huang
Shukang Yin
Haojia Lin
Jinfa Huang
Chaoyou Fu
Jiayi Ji

Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods employ post-hoc low-response token pruning in decoder layers, they overlook the input-level semantic correlation between visual tokens and instructions (query). In this paper, we propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models (LVLMs) for visual token assignment based on query-oriented frame-level importance assessment. The query-oriented token selection is crucial as it aligns visual processing with task-specific requirements, optimizing token budget utilization while preserving semantically relevant content. Specifically, (i) QuoTA strategically allocates frame-level importance scores based on query relevance, enabling one-time visual token assignment before cross-modal interactions in decoder layers, (ii) we decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring, and (iii) QuoTA offers a plug-and-play functionality that extends to existing LVLMs. Extensive experimental results demonstrate that implementing QuoTA with LLaVA-Video-7B yields an average performance improvement of 3.2% across six benchmarks (including Video-MME and MLVU) while operating within an identical visual token budget as the baseline.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Aligning Instance Brownian Bridge with Texts for Open-Vocabulary Video Instance Segmentation

Zesen Cheng
Kehan Li
Li Hao
Peng Jin
Xiawu Zheng
Chang Liu
Jie Chen

Temporally locating objects with arbitrary class texts is the primary pursuit of open-vocabulary Video Instance Segmentation (VIS). Because of the insufficient vocabulary of video data, previous methods leverage the image-text pretraining model for recognizing object instances by separately aligning each frame with class texts. As a result, the separation breaks the instance movement context of videos and requires a lot of inference overhead. To tackle these issues, we propose BridgeText Alignment (BTA) to link frame-level instance representations as a Brownian Bridge. On one hand, we can calculate the global descriptor of a Brownian bridge for capturing instance dynamics, which enables extra considering temporal information rather than only static information of each frame for aligning with texts. On the other hand, according to the goal-conditioned property of the Brownian bridge, we can estimate the middle frame features via the start and the end frame features so the global feature calculation of a Brownian bridge only needs to infer a few frames, which largely reduces inference overhead. We term our overall pipeline as BriVIS. Following the training settings of previous works, BriVIS surpasses the SOTA (OV2Seg) by a clear margin. For example, on the challenging large-vocabulary datasets (BURST, LVVIS), BriVIS achieves 5.7 and 20.9 mAP, which exhibits +2.2∼+6.7 mAP improvement compared to OV2Seg. Furthermore, after training via BTA, using only the head and the tail frames for alignment improves the speed by 32% (2.77 → 1.88 s/iter) while just decreasing the performance by 0.2 mAP (21.1 → 20.9 mAP).

PDF Details DOI

ICML Conference 2025 Conference Paper

BAME: Block-Aware Mask Evolution for Efficient N: M Sparse Training

Chenyi Yang 0002
Wenjie Nie
Yuxin Zhang 0002
Yuhang Wu 0004
Xiawu Zheng
Guannan Jiang
Rongrong Ji

N: M sparsity stands as a progressively important tool for DNN compression, achieving practical speedups by stipulating at most N non-zero components within M sequential weights. Unfortunately, most existing works identify the N: M sparse mask through dense backward propagation to update all weights, which incurs exorbitant training costs. In this paper, we introduce BAME, a method that maintains consistent sparsity throughout the N: M sparse training process. BAME perpetually keeps both sparse forward and backward propagation, while iteratively performing weight pruning-and-regrowing within designated weight blocks to tailor the N: M mask. These blocks are selected through a joint assessment based on accumulated mask oscillation frequency and expected loss reduction of mask adaptation, thereby ensuring stable and efficient identification of the optimal N: M mask. Our empirical results substantiate the effectiveness of BAME, illustrating it performs comparably to or better than previous works that fully maintaining dense backward propagation during training. For instance, BAME attains a 72. 0% top-1 accuracy while training a 1: 16 sparse ResNet-50 on ImageNet, eclipsing SR-STE by 0. 5%, despite achieving 2. 37 training FLOPs reduction. Code is released at https: //github. com/BAME-xmu/BAME

Details

ICML Conference 2025 Conference Paper

Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective

Qingchuan Ma
Yuhang Wu 0004
Xiawu Zheng
Rongrong Ji

In this paper, we aim to establish a simple, effective, and theoretically grounded benchmark for rigorously probing abstract reasoning in Large Language Models (LLMs). To achieve this, we first develop a mathematic framework that defines abstract reasoning as the ability to: (i) extract essential patterns independent of surface representations, and (ii) apply consistent rules to these abstract patterns. Based on this framework, we introduce two novel complementary metrics: $\Gamma$ measures basic reasoning accuracy, while $\Delta$ quantifies a model’s reliance on specific symbols rather than underlying patterns - a key indicator of true abstraction versus mere memorization. To implement this measurement, we design a benchmark: systematic symbol remapping in rule-based tasks, which forces models to demonstrate genuine pattern recognition beyond superficial token matching. Extensive LLM evaluations using this benchmark (commercial API models, 7B-70B, multi-agent) reveal: 1) critical limitations in non-decimal arithmetic and symbolic reasoning; 2) persistent abstraction gaps despite chain-of-thought prompting; and 3) $\Delta$’s effectiveness in robustly measuring memory dependence by quantifying performance degradation under symbol remapping, particularly highlighting operand-specific memorization. These findings underscore that current LLMs, despite domain-specific strengths, still lack robust abstract reasoning, highlighting key areas for future improvement.

Details

ICML Conference 2025 Conference Paper

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective

Weizhong Huang
Yuxin Zhang 0002
Xiawu Zheng
Fei Chao 0001
Rongrong Ji

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of "reconstruction error explosion" in existing LLMs sparsification methods. This refers to the cumulative effect of reconstruction errors throughout the sparsification process, where errors from earlier layers propagate and amplify in subsequent layers. As a result, the overall reconstruction error increases significantly, leading to a substantial degradation in model performance. Through theoretical analysis, we derive a simple yet effective approach to layer-wise sparsity allocation that mitigates this issue. Our method uses a monotonically increasing arithmetic progression, reducing the process of determining sparsity rates for multiple layers to the determination of a single common difference hyperparameter. Remarkably, this allows for the optimal layer-wise sparsity rates to be identified with just a few trials. Both our theoretical analysis and experimental results demonstrate that this sparsity allocation scheme is near optimal. Extensive experiments show that our method significantly improves the performance of sparse LLMs across various architectures, outperforming existing layer-wise sparsity methods. Furthermore, it enhances the performance of various compression techniques and is applicable to vision and multimodal models. Notably, our method achieves a reduction of 52. 10 in perplexity for the 70% sparse LLaMA2-7B model obtained via Wanda, improves average zero-shot accuracy by 10. 50%, and delivers speedups of 2. 63$\times$ and 2. 23$\times$ on CPU and GPU, respectively. Code is available at https: //github. com/wzhuang-xmu/ATP.

Details

NeurIPS Conference 2025 Conference Paper

Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective

Weizhong Huang
Yuxin Zhang
Xiawu Zheng
Fei Chao
Rongrong Ji
Liujuan Cao

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models but face prohibitive memory demands due to massive parameterization. Existing pruning methods rely on heuristic metrics or impractical enumeration of expert subsets, leading to suboptimal performance or scalability. In this paper, we propose Shapley-MoE, an efficient pruning method for MoE models inspired by cooperative game theory. By quantifying each expert’s contribution via Shapley value, our method identifies important experts without exhaustive combination evaluations. To overcome the NP-hard complexity of exact Shapley computation, we introduce a Monte Carlo sampling strategy for efficient approximation that reduces complexity to quadratic time. However, vanilla Monte Carlo sampling still faces issues of insufficient estimation accuracy and low sampling efficiency. To address these issues, we further propose two novel methods to improve sampling accuracy and efficiency: (1) Early Truncation, which early terminates unstable sampling steps caused by overly small expert subsets, and (2) Router-Guided Importance Sampling, which prioritize sampling important expert subsets using gating activation probabilities. Both theoretical and experimental analyses show that both methods can accelerate Shapley value estimation and improve accuracy. Extensive empirical evaluations demonstrate that our pruned MoE models outperform existing expert pruning methods. Notably, when applied to the Qwen2-57B-A14B model, our method reduces the number of experts by 25% with only a 0. 92 increase in perplexity and over 96. 4% of the average zero-shot accuracy is maintained.

PDF Details

AAAI Conference 2025 Conference Paper

Dynamic Clustering Convolutional Neural Network

Tanzhe Li
Baochang Zhang
Jiayi Lyu
Xiawu Zheng
Guodong Guo
Taisong Jin

Convolutional neural networks (CNNs) have been playing a dominant role in computer vision. However, the existing approaches of using local window modeling in popular CNNs lack flexibility and hinder their ability to capture long-range dependencies of objects in an image. To overcome these limitations, we propose a novel CNN architecture, termed Dynamic Clustering Convolutional Neural Network (DCCNeXt). The proposed DCCNeXt takes a unique approach by employing global clustering to group image patches with similar semantics into clusters that are then convolved using the shared convolution kernels. To address the high computational complexity of global clustering, the feature vectors from each patch's subspace are extracted for efficient clustering, which makes the proposed model widely compatible with the downstream vision tasks. The extensive experiments of image classification, object detection, instance segmentation, and semantic segmentation on the benchmark datasets demonstrate that the proposed DCCNeXt outperforms the mainstream Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Vision Multi-layer Perceptrons (MLPs), Vision Graph Neural Networks (GNNs), and Vision Mambas. We anticipate that this study will provide a new perspective and a promising avenue for the design of convolutional neural networks.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Dynamic Low-Rank Sparse Adaptation for Large Language Models

Weizhong Huang
Yuxin Zhang 0002
Xiawu Zheng
Yang Liu 0005
Jing Lin
Yiwu Yao
Rongrong Ji

Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Adaptation (LoRA) to fine-tune the sparse LLMs offers an intuitive approach to counter this predicament, while it holds shortcomings include: 1) The inability to integrate LoRA weights into sparse LLMs post-training, and 2) Insufficient performance recovery at high sparsity ratios. In this paper, we introduces dynamic $\textbf{Lo}$w-rank $\textbf{S}$parse $\textbf{A}$daptation $\textbf{(LoSA)}$, a novel method that seamlessly integrates low-rank adaptation into LLM sparsity within a unified framework, thereby enhancing the performance of sparse LLMs without increasing the inference latency. In particular, LoSA dynamically sparsifies the LoRA outcomes based on the corresponding sparse weights during fine-tuning, thus guaranteeing that the LoRA module can be integrated into the sparse LLMs post-training. Besides, to achieve the optimal sparse model architecture, LoSA leverages Representation Mutual Information (RMI) as an indicator to determine the importance of layers, thereby dynamically determining the optimal layer-wise sparsity rates during fine-tuning. Predicated on this, LoSA adjusts the rank of the LoRA module based on the variability in layer-wise reconstruction errors, allocating an appropriate fine-tuning for each layer to reduce the output discrepancies between dense and sparse LLMs. Extensive experiments tell that LoSA can efficiently boost the efficacy of sparse LLMs within a few hours, without introducing any additional inferential burden. For example, LoSA reduced the perplexity of sparse LLaMA-2-7B by $\textbf{68.73}$$\downarrow$ and increased zero-shot accuracy by $\textbf{16.32}$%$\uparrow$, achieving a $\textbf{2.60$\times$}$ speedup on CPU and $\textbf{2.23$\times$}$ speedup on GPU, requiring only $\textbf{45 minutes}$ of fine-tuning on $\textbf{a single}$ NVIDIA A100 80GB GPU. Code is available at https://github.com/wzhuang-xmu/LoSA.

Details

ICLR Conference 2025 Conference Paper

Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Gen Luo
Yiyi Zhou
Yuxin Zhang 0002
Xiawu Zheng
Xiaoshuai Sun
Rongrong Ji

In existing multimodal large language models (MLLMs), image resolution plays a significant role for granular visual recognition. However, directly increasing image resolution leads to expensive computational cost for MLLMs. In this paper, we reveal that a combination of low- and high-resolution visual features can efficiently mitigate this shortcoming. Based on this principle, we propose a novel and efficient method for MLLMs, termed Mixture-of-Resolution Adaptation (MRA). In particular, MRA adopts two visual pathways for images of different resolutions, where high-resolution visual information is embedded into the low-resolution pathway via the novel mixture-of-resolution adapters (MR-Adapters). This design also greatly reduces the input sequence length of MLLMs. To validate MRA, we apply it to a recent MLLM called LLaVA, and term the new model LLaVA-HR. We conduct extensive experiments on 17 vision-language (VL) tasks, which show that LLaVA-HR outperforms existing MLLMs on 15 VL tasks, e.g., +5.2\% on TextVQA. More importantly, both training and inference of LLaVA-HR remain efficient with MRA, e.g., 20 training hours and faster inference speed than LLaVA-NeXT. Source codes are released at: https://github.com/luogen1996/LLaVA-HR.

Details

AAAI Conference 2025 Conference Paper

Feature Denoising Diffusion Model for Blind Image Quality Assessment

Xudong Li
Yan Zhang
Yunhang Shen
Ke Li
Runze Hu
Xiawu Zheng
Sicheng Zhao

Blind Image Quality Assessment (BIQA) aims to evaluate image quality in line with human perception, without reference benchmarks. Currently, deep learning BIQA methods typically depend on using features from high-level tasks for transfer learning. However, the inherent differences between BIQA and these high-level tasks inevitably introduce noise into the quality-aware features. In this paper, we take an initial step toward exploring the diffusion model for feature denoising in BIQA, namely Perceptual Feature Diffusion for IQA (PFD-IQA), which aims to remove noise from quality-aware features. Specifically, 1) we propose a Perceptual Prior Discovery and Aggregation module to establish two auxiliary tasks to discover potential low-level features in images that are used to aggregate perceptual textual prompt conditions for the diffusion model. 2) we propose a Perceptual Conditional Feature Refinement strategy, which matches noisy features to predefined denoising trajectories and then performs exact feature denoising based on textual prompt conditions. By incorporating a lightweight denoiser and requiring only a few feature denoising steps (e.g., just five iterations), our PFD-IQA framework achieves superior performance across eight standard BIQA datasets, validating its effectiveness.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Learning Interleaved Image-Text Comprehension in Vision-Language Large Models

Chenyu Zhou
Mengdan Zhang
Peixian Chen
Chaoyou Fu
Yunhang Shen
Xiawu Zheng
Xing Sun 0001
Rongrong Ji

The swift progress of Multi-modal Large Models (MLLMs) has showcased their impressive ability to tackle tasks blending vision and language. Yet, most current models and benchmarks cater to scenarios with a narrow scope of visual and textual contexts. These models often fall short when faced with complex comprehension tasks, which involve navigating through a plethora of irrelevant and potentially misleading information in both text and image forms. To bridge this gap, we introduce a new, more demanding task known as Interleaved Image-Text Comprehension (IITC). This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions and to follow intricate instructions to pinpoint the relevant image. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA), to refine image-text correlation skills. Our evaluation of four leading closed-source models, as well as various open-source models using VEGA, underscores the rigorous nature of IITC. Even the most advanced models, such as Gemini-1.5-pro and GPT4V, only achieved modest success. By employing a multi-task, multi-scale post-training strategy, we have set a robust baseline for MLLMs on the IITC task, attaining an $85.8\%$ accuracy rate in image association and a $0.508$ Rouge score. These results validate the effectiveness of our dataset in improving MLLMs capabilities for nuanced image-text comprehension.

Details

NeurIPS Conference 2025 Conference Paper

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Chaoyou Fu
Peixian Chen
Yunhang Shen
Yulei Qin
Mengdan Zhang
Xu Lin
Jinrui Yang
Xiawu Zheng

Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to fully reflect the performance of MLLM, lacking a comprehensive evaluation. In this paper, we fill in this blank, presenting the first comprehensive MLLM Evaluation benchmark MME. It measures both perception and cognition abilities on a total of 14 subtasks. In order to avoid data leakage that may arise from direct use of public datasets for evaluation, the annotations of instruction-answer pairs are all manually designed. The concise instruction design allows us to fairly compare MLLMs, instead of struggling in prompt engineering. Besides, with such an instruction, we can also easily carry out quantitative statistics. A total of 30 advanced MLLMs are comprehensively evaluated on our MME, which not only suggests that existing MLLMs still have a large room for improvement, but also reveals the potential directions for the subsequent model optimization. The data are released at the project page: https: //github. com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation.

PDF Details

ICLR Conference 2025 Conference Paper

Multimodal Quantitative Language for Generative Recommendation

Jianyang Zhai
Zi-Feng Mai
Chang-Dong Wang 0001
Feidiao Yang
Xiawu Zheng
Hui Li 0057
Yonghong Tian 0001

Generative recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. Most existing methods attempt to leverage prior knowledge embedded in Pre-trained Language Models (PLMs) to improve the recommendation performance. However, they often fail to accommodate the differences between the general linguistic knowledge of PLMs and the specific needs of recommendation systems. Moreover, they rarely consider the complementary knowledge between the multimodal information of items, which represents the multi-faceted preferences of users. To facilitate efficient recommendation knowledge transfer, we propose a novel approach called Multimodal Quantitative Language for Generative Recommendation (MQL4GRec). Our key idea is to transform items from different domains and modalities into a unified language, which can serve as a bridge for transferring recommendation knowledge. Specifically, we first introduce quantitative translators to convert the text and image content of items from various domains into a new and concise language, known as quantitative language, with all items sharing the same vocabulary. Then, we design a series of quantitative language generation tasks to enrich quantitative language with semantic information and prior knowledge. Finally, we achieve the transfer of recommendation knowledge from different domains and modalities to the recommendation task through pre-training and fine-tuning. We evaluate the effectiveness of MQL4GRec through extensive experiments and comparisons with existing methods, achieving improvements over the baseline by 11.18\%, 14.82\%, and 7.95\% on the NDCG metric across three different datasets, respectively.

Details

ICML Conference 2025 Conference Paper

polybasic Speculative Decoding Through a Theoretical Perspective

Ruilin Wang
Huixia Li
Yuexiao Ma
Xiawu Zheng
Fei Chao 0001
Xuefeng Xiao 0001
Rongrong Ji

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output distribution. However, existing work typically relies on a dualistic draft-verify framework and lacks rigorous theoretical grounding. In this paper, we introduce a novel polybasic speculative decoding framework, underpinned by a comprehensive theoretical analysis. Specifically, we prove a fundamental theorem that characterizes the optimal inference time for multi-model speculative decoding systems, shedding light on how to extend beyond the dualistic approach to a more general polybasic paradigm. Through our theoretical investigation of multi-model token generation, we expose and optimize the interplay between model capabilities, acceptance lengths, and overall computational cost. Our framework supports both standalone implementation and integration with existing speculative techniques, leading to accelerated performance in practice. Experimental results across multiple model families demonstrate that our approach yields speedup ratios ranging from $3. 31\times$ to $4. 01\times$ for LLaMA2-Chat 7B, up to $3. 87 \times$ for LLaMA3-8B, up to $4. 43 \times$ for Vicuna-7B and up to $3. 85 \times$ for Qwen2-7B—all while preserving the original output distribution. We release our theoretical proofs and implementation code to facilitate further investigation into polybasic speculative decoding.

Details

NeurIPS Conference 2025 Conference Paper

Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension

Yongdong Luo
Xiawu Zheng
Guilin Li
Shukang Yin
Haojia Lin
Chaoyou Fu
Jinfa Huang
Jiayi Ji

Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions. However, fine-tuning LVLMs would require extensive high-quality data and substantial GPU resources, while GPT-based agents would rely on proprietary models (e. g. , GPT-4o). In this paper, we propose Video Retrieval-Augmented Generation (Video-RAG), a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment while providing additional information beyond the visual content. Specifically, we leverage open-source external tools to extract visually-aligned information from pure video data (e. g. , audio, optical character, and object detection), and incorporate the extracted information into an existing LVLM as auxiliary texts, alongside video frames and queries, in a plug-and-play manner. Our Video-RAG offers several key advantages: (i) lightweight with low computing overhead due to single-turn retrieval; (ii) easy implementation and compatibility with any LVLM; and (iii) significant, consistent performance gains across long video understanding benchmarks, including Video-MME, MLVU, and LongVideoBench. Notably, our model demonstrates superior performance over proprietary models like Gemini-1. 5-Pro and GPT-4o when utilized with a 72B model.

PDF Details

NeurIPS Conference 2025 Conference Paper

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Chaoyou Fu
Haojia Lin
Xiong Wang
Yifan Zhang
Yunhang Shen
Xiaoyu Liu
Haoyu Cao
Zuwei Long

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing against state-of-the-art counterparts across benchmarks for image, video, and speech, we demonstrate that our omni model is equipped with both strong visual and speech capabilities, making omni understanding and interaction.

PDF Details

NeurIPS Conference 2025 Conference Paper

Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs

Xudong Li
Mengdan Zhang
Peixian Chen
Xiawu Zheng
Yan Zhang
Jingyuan Zheng
Yunhang Shen
Ke Li

Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing methods using Direct Preference Optimization (DPO) constrain optimization to a solitary image reference within the input sequence, neglecting holistic context modeling. To address this, we propose Context-to-Cue Direct Preference Optimization (CcDPO), a multi-level preference optimization framework that enhances per-image perception in multi-image settings by zooming into visual clues—from sequential context to local details. Our approach features two sequentially dependent components: (i) Context-Level Optimization: By introducing low-cost sequence preference pairs, we optimize the model to distinguish between complete and disrupted multi-image contexts, thereby correcting cognitive biases in MLLMs’ multi-image understanding. (ii) Needle-Level Optimization: By integrating region-specific visual prompts with multimodal preference supervision, we direct the model’s attention to critical visual details, effectively suppressing perceptual biases toward fine-grained visual information. To support scalable optimization, we also construct MultiScope-42k, an automatically generated multi-image dataset with hierarchical preference pairs. Experiments show that CcDPO significantly reduces hallucinations and yields consistent performance gains across general single- and multi-image tasks. Codes are available at https: //github. com/LXDxmu/CcDPO.

PDF Details

ICML Conference 2024 Conference Paper

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity

Xudong Li
Timin Gao
Runze Hu
Yan Zhang 0109
Shengchuan Zhang
Xiawu Zheng
Jingyuan Zheng
Yunhang Shen

The current state-of-the-art No-Reference Image Quality Assessment (NR-IQA) methods typically rely on feature extraction from upstream semantic backbone networks, assuming that all extracted features are relevant. However, we make a key observation that not all features are beneficial, and some may even be harmful, necessitating careful selection. Empirically, we find that many image pairs with small feature spatial distances can have vastly different quality scores, indicating that the extracted features may contain quality-irrelevant noise. To address this issue, we propose a Quality-Aware Feature Matching IQA Metric (QFM-IQM) that employs an adversarial perspective to remove harmful semantic noise features from the upstream task. Specifically, QFM-IQM enhances the semantic noise distinguish capabilities by matching image pairs with similar quality scores but varying semantic features as adversarial semantic noise and adaptively adjusting the upstream task’s features by reducing sensitivity to adversarial noise perturbation. Furthermore, we utilize a distillation framework to expand the dataset and improve the model’s generalization ability. Extensive experiments conducted on eight standard IQA datasets have demonstrated the effectiveness of our proposed QFM-IQM.

Details

ICLR Conference 2024 Conference Paper

AffineQuant: Affine Transformation Quantization for Large Language Models

Yuexiao Ma
Huixia Li
Xiawu Zheng
Feng Ling
Xuefeng Xiao 0001
Rui Wang 0089
Shilei Wen
Fei Chao 0001

The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its noteworthy compression efficiency and cost-effectiveness in the context of training. Existing PTQ methods for LLMs limit the optimization scope to scaling transformations between pre- and post-quantization weights. This constraint results in significant errors after quantization, particularly in low-bit configurations. In this paper, we advocate for the direct optimization using equivalent Affine transformations in PTQ (AffineQuant). This approach extends the optimization scope and thus significantly minimizing quantization errors. Additionally, by employing the corresponding inverse matrix, we can ensure equivalence between the pre- and post-quantization outputs of PTQ, thereby maintaining its efficiency and generalization capabilities. To ensure the invertibility of the transformation during optimization, we further introduce a gradual mask optimization method. This method initially focuses on optimizing the diagonal elements and gradually extends to the other elements. Such an approach aligns with the Levy-Desplanques theorem, theoretically ensuring invertibility of the transformation. As a result, significant performance improvements are evident across different LLMs on diverse datasets. Notably, these improvements are most pronounced when using very low-bit quantization, enabling the deployment of large models on edge devices. To illustrate, we attain a C4 perplexity of $15.76$ (2.26$\downarrow$ vs $18.02$ in OmniQuant) on the LLaMA2-$7$B model of W$4$A$4$ quantization without overhead. On zero-shot tasks, AffineQuant achieves an average of $58.61\%$ accuracy ( $1.98\%\uparrow$ vs $56.63$ in OmniQuant) when using $4$/$4$-bit quantization for LLaMA-$30$B, which setting a new state-of-the-art benchmark for PTQ in LLMs. Codes are available at: https://github.com/bytedance/AffineQuant.

Details

AAAI Conference 2024 Conference Paper

Binding-Adaptive Diffusion Models for Structure-Based Drug Design

Zhilin Huang
Ling Yang
Zaixi Zhang
Xiangxin Zhou
Yu Bao
Xiawu Zheng
Yuwei Yang
Yu Wang

Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D space for molecular generation. To address this problem, we propose a novel framework, namely Binding-Adaptive Diffusion Models (BindDM). In BindDM, we adaptively extract subcomplex, the essential part of binding sites responsible for protein-ligand interactions. Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information. We iterate this hierarchical complex-subcomplex process with cross-hierarchy interaction node for adequately fusing global binding context between the complex and its corresponding subcomplex. Empirical studies on the CrossDocked2020 dataset show BindDM can generate molecules with more realistic 3D structures and higher binding affinities towards the protein targets, with up to -5.92 Avg. Vina Score, while maintaining proper molecular properties. Our code is available at https://github.com/YangLing0818/BindDM

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion

Quanmin Liang
Zhilin Huang
Xiawu Zheng
Feidiao Yang
Jun Peng
Kai Huang
Yonghong Tian

Current Event Stream Super-Resolution (ESR) methods overlook the redundant and complementary information present in positive and negative events within the event stream, employing a direct mixing approach for super-resolution, which may lead to detail loss and inefficiency. To address these issues, we propose an efficient Recursive Multi-Branch Information Fusion Network (RMFNet) that separates positive and negative events for complementary information extraction, followed by mutual supplementation and refinement. Particularly, we introduce Feature Fusion Modules (FFM) and Feature Exchange Modules (FEM). FFM is designed for the fusion of contextual information within neighboring event streams, leveraging the coupling relationship between positive and negative events to alleviate the misleading of noises in the respective branches. FEM efficiently promotes the fusion and exchange of information between positive and negative branches, enabling superior local information enhancement and global information complementation. Experimental results demonstrate that our approach achieves over 17% and 31% improvement on synthetic and real datasets, accompanied by a 2. 3x acceleration. Furthermore, we evaluate our method on two downstream event-driven applications, i. e. , object recognition and video reconstruction, achieving remarkable results that outperform existing methods. Our code and Supplementary Material are available at https: //github. com/Lqm26/RMFNet.

PDF Details DOI

ICML Conference 2024 Conference Paper

Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment

Xudong Li
Runze Hu
Jingyuan Zheng
Yan Zhang 0109
Shengchuan Zhang
Xiawu Zheng
Ke Li 0015
Yunhang Shen

Blind Image Quality Assessment (BIQA) mirrors subjective made by human observers. Generally, humans favor comparing relative qualities over predicting absolute qualities directly. However, current BIQA models focus on mining the "local" context, i. e. , the relationship between information among individual images and the absolute quality of the image, ignoring the "global" context of the relative quality contrast among different images in the training data. In this paper, we present the Perceptual Context and Sensitivity BIQA (CSIQA), a novel contrastive learning paradigm that seamlessly integrates "global” and "local” perspectives into the BIQA. Specifically, the CSIQA comprises two primary components: 1) A Quality Context Contrastive Learning module, which is equipped with different contrastive learning strategies to effectively capture potential quality correlations in the global context of the dataset. 2) A Quality-aware Mask Attention Module, which employs the random mask to ensure the consistency with visual local sensitivity, thereby improving the model’s perception of local distortions. Extensive experiments on eight standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods.

Details

ICML Conference 2024 Conference Paper

Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation

Zhilin Huang
Ling Yang 0006
Xiangxin Zhou
Chujun Qin
Yijie Yu 0001
Xiawu Zheng
Zikun Zhou
Wentao Zhang 0001

Generating ligand molecules that bind to specific protein targets via generative models holds substantial promise for advancing structure-based drug design. Existing methods generate molecules from scratch without reference or template ligands, which poses challenges in model optimization and may yield suboptimal outcomes. To address this problem, we propose an innovative interaction-based retrieval-augmented diffusion model named IRDiff to facilitate target-aware molecule generation. IRDiff leverages a curated set of ligand references, i. e. , those with desired properties such as high binding affinity, to steer the diffusion model towards synthesizing ligands that satisfy design criteria. Specifically, we utilize a protein-molecule interaction network (PMINet), which is pretrained with binding affinity signals to: (i) retrieve target-aware ligand molecules with high binding affinity to serve as references, and (ii) incorporate essential protein-ligand binding structures for steering molecular diffusion generation with two effective augmentation mechanisms, i. e. , retrieval augmentation and self augmentation. Empirical studies on CrossDocked2020 dataset show IRDiff can generate molecules with more realistic 3D structures and achieve state-of-the-art binding affinities towards the protein targets, while maintaining proper molecular properties. The codes and models are available at https: //github. com/YangLing0818/IRDiff

Details

ICLR Conference 2024 Conference Paper

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

Sirui Hong
Mingchen Zhuge
Jonathan Chen
Xiawu Zheng
Yuheng Cheng
Jinlin Wang
Ceyao Zhang
Zili Wang

Recently, remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Previous LLM-based multi-agent systems can already solve simple dialogue tasks. More complex tasks, however, face challenges through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems.

Details

ICML Conference 2024 Conference Paper

Outlier-aware Slicing for Post-Training Quantization in Vision Transformer

Yuexiao Ma
Huixia Li
Xiawu Zheng
Feng Ling
Xuefeng Xiao 0001
Rui Wang 0089
Shilei Wen
Fei Chao 0001

Post-Training Quantization (PTQ) is a vital technique for network compression and acceleration, gaining prominence as model sizes increase. This paper addresses a critical challenge in PTQ: the severe impact of outliers on the accuracy of quantized transformer architectures. Specifically, we introduce the concept of ‘reconstruction granularity’ as a novel solution to this issue, which has been overlooked in previous works. Our work provides theoretical insights into the role of reconstruction granularity in mitigating the outlier problem in transformer models. This theoretical framework is supported by empirical analysis, demonstrating that varying reconstruction granularities significantly influence quantization performance. Our findings indicate that different architectural designs necessitate distinct optimal reconstruction granularities. For instance, the multi-stage Swin Transformer architecture benefits from finer granularity, a deviation from the trends observed in ViT and DeiT models. We further develop an algorithm for determining the optimal reconstruction granularity for various ViT models, achieving state-of-the-art (SOTA) performance in PTQ. For example, applying our method to $4$-bit quantization, the Swin-Base model achieves a Top-1 accuracy of $82. 24%$ on the ImageNet classification task. This result surpasses the RepQ-ViT by $3. 92%$ ($82. 24%$ VS $78. 32%$). Similarly, our approach elevates the ViT-Small to a Top-1 accuracy of $80. 50%$, outperforming NoisyQuant by $3. 64%$ ($80. 50%$ VS $76. 86%$). Codes are available in Supplementary Materials.

Details

ICLR Conference 2024 Conference Paper

Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models

Zhilin Huang
Ling Yang 0006
Xiangxin Zhou
Zhilong Zhang
Wentao Zhang 0001
Xiawu Zheng
Jie Chen 0001
Yu Wang 0027

Generating 3D ligand molecules that bind to specific protein targets via diffusion models has shown great promise for structure-based drug design. The key idea is to disrupt molecules into noise through a fixed forward process and learn its reverse process to generate molecules from noise in a denoising way. However, existing diffusion models primarily focus on incorporating protein-ligand interaction information solely in the reverse process, and neglect the interactions in the forward process. The inconsistency between forward and reverse processes may impair the binding affinity of generated molecules towards target protein. In this paper, we propose a novel Interaction Prior-guided Diffusion model (IPDiff) for the protein-specific 3D molecular generation by introducing geometric protein-ligand interactions into both diffusion and sampling process. Specifically, we begin by pretraining a protein-ligand interaction prior network (IPNet) by utilizing the binding affinity signals as supervision. Subsequently, we leverage the pretrained prior network to (1) integrate interactions between the target protein and the molecular ligand into the forward process for adapting the molecule diffusion trajectories (prior-shifting), and (2) enhance the binding-aware molecule sampling process (prior-conditioning). Empirical studies on CrossDocked2020 dataset show IPDiff can generate molecules with more realistic 3D structures and state-of-the-art binding affinities towards the protein targets, with up to -6.42 Avg. Vina Score, while maintaining proper molecular properties. https://github.com/YangLing0818/IPDiff

Details

AAAI Conference 2024 Conference Paper

Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning

Wensheng Pan
Timin Gao
Yan Zhang
Xiawu Zheng
Yunhang Shen
Ke Li
Runze Hu
Yutao Liu

Blind Image Quality Assessment (BIQA) aims to simulate human assessment of image quality. It has a great demand for labeled data, which is often insufficient in practice. Some researchers employ unsupervised methods to address this issue, which is challenging to emulate the human subjective system. To this end, we introduce a unified framework that combines semi-supervised and incremental learning to address the mentioned issue. Specifically, when training data is limited, semi-supervised learning is necessary to infer extensive unlabeled data. To facilitate semi-supervised learning, we use knowledge distillation to assign pseudo-labels to unlabeled data, preserving analytical capability. To gradually improve the quality of pseudo labels, we introduce incremental learning. However, incremental learning can lead to catastrophic forgetting. We employ Experience Replay by selecting representative samples during multiple rounds of semi-supervised learning, to alleviate forgetting and ensure model stability. Experimental results show that the proposed approach achieves state-of-the-art performance across various benchmark datasets. After being trained on the LIVE dataset, our method can be directly transferred to the CSIQ dataset. Compared with other methods, it significantly outperforms unsupervised methods on the CSIQ dataset with a marginal performance drop (-0.002) on the LIVE dataset. In conclusion, our proposed method demonstrates its potential to tackle the challenges in real-world production processes.

PDF Details DOI

ICLR Conference 2023 Conference Paper

A Unified Framework for Soft Threshold Pruning

Yanqi Chen
Zhengyu Ma
Wei Fang 0006
Xiawu Zheng
Zhaofei Yu
Yonghong Tian 0001

Soft threshold pruning is among the cutting-edge pruning methods with state-of-the-art performance. However, previous methods either perform aimless searching on the threshold scheduler or simply set the threshold trainable, lacking theoretical explanation from a unified perspective. In this work, we reformulate soft threshold pruning as an implicit optimization problem solved using the Iterative Shrinkage-Thresholding Algorithm (ISTA), a classic method from the fields of sparse recovery and compressed sensing. Under this theoretical framework, all threshold tuning strategies proposed in previous studies of soft threshold pruning are concluded as different styles of tuning $L_1$-regularization term. We further derive an optimal threshold scheduler through an in-depth study of threshold scheduling based on our framework. This scheduler keeps $L_1$-regularization coefficient stable, implying a time-invariant objective function from the perspective of optimization. In principle, the derived pruning algorithm could sparsify any mathematical model trained via SGD. We conduct extensive experiments and verify its state-of-the-art performance on both Artificial Neural Networks (ResNet-50 and MobileNet-V1) and Spiking Neural Networks (SEW ResNet-18) on ImageNet datasets. On the basis of this framework, we derive a family of pruning methods, including sparsify-during-training, early pruning, and pruning at initialization. The code is available at https://github.com/Yanqi-Chen/LATS.

Details

AAAI Conference 2023 Conference Paper

Data-Efficient Image Quality Assessment with Attention-Panel Decoder

Guanyi Qin
Runze Hu
Yutao Liu
Xiawu Zheng
Haotian Liu
Xiu Li
Yan Zhang

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a novel BIQA pipeline based on the Transformer architecture, which achieves an efficient quality-aware feature representation with much fewer data. More specifically, we consider the traditional fine-tuning in BIQA as an interpretation of the pre-trained model. In this way, we further introduce a Transformer decoder to refine the perceptual information of the CLS token from different perspectives. This enables our model to establish the quality-aware feature manifold efficiently while attaining a strong generalization capability. Meanwhile, inspired by the subjective evaluation behaviors of human, we introduce a novel attention panel mechanism, which improves the model performance and reduces the prediction uncertainty simultaneously. The proposed BIQA method maintains a light-weight design with only one layer of the decoder, yet extensive experiments on eight standard BIQA datasets (both synthetic and authentic) demonstrate its superior performance to the state-of-the-art BIQA methods, i.e., achieving the SRCC values of 0.875 (vs. 0.859 in LIVEC) and 0.980 (vs. 0.969 in LIVE). Checkpoints, logs and code will be available at https://github.com/narthchin/DEIQT.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

Yu Wang
Zhun Zhong
Pengchong Qiao
Xuxin Cheng
Xiawu Zheng
Chang Liu
Nicu Sebe
Rongrong Ji

Open-world Semi-Supervised Learning (OSSL) is a realistic and challenging task, aiming to classify unlabeled samples from both seen and novel classes using partially labeled samples from the seen classes. Previous works typically explore the relationship of samples as priors on the pre-defined single-granularity labels to help novel class recognition. In fact, classes follow a taxonomy and samples can be classified at multiple levels of granularity, which contains more underlying relationships for supervision. We thus argue that learning with single-granularity labels results in sub-optimal representation learning and inaccurate pseudo labels, especially with unknown classes. In this paper, we take the initiative to explore and propose a uniformed framework, called Taxonomic context prIors Discovering and Aligning (TIDA), which exploits the relationship of samples under various granularity. It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i. e. , sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels. Specifically, TIDA comprises two components: i) A taxonomic context discovery module that constructs a set of hierarchical prototypes in the latent space to discover the underlying taxonomic context priors; ii) A taxonomic context-based prediction alignment module that enforces consistency across hierarchical predictions to build the reliable relationship between classes among various granularity and provide additions supervision. We demonstrate that these two components are mutually beneficial for an effective OSSL framework, which is theoretically explained from the perspective of the EM algorithm. Extensive experiments on seven commonly used datasets show that TIDA can significantly improve the performance and achieve a new state of the art. The source codes are publicly available at https: //github. com/rain305f/TIDA.

PDF Details

AAAI Conference 2023 Conference Paper

OMPQ: Orthogonal Mixed Precision Quantization

Yuexiao Ma
Taisong Jin
Xiawu Zheng
Yan Wang
Huixia Li
Yongjian Wu
Guannan Jiang
Wei Zhang

To bridge the ever-increasing gap between deep neural networks' complexity and hardware capability, network quantization has attracted more and more research attention. The latest trend of mixed precision quantization takes advantage of hardware's multiple bit-width arithmetic operations to unleash the full potential of network quantization. However, existing approaches rely heavily on an extremely time-consuming search process and various relaxations when seeking the optimal bit configuration. To address this issue, we propose to optimize a proxy metric of network orthogonality that can be efficiently solved with linear programming, which proves to be highly correlated with quantized model accuracy and bit-width. Our approach significantly reduces the search time and the required data amount by orders of magnitude, but without a compromise on quantization accuracy. Specifically, we achieve 72.08% Top-1 accuracy on ResNet-18 with 6.7Mb parameters, which does not require any searching iterations. Given the high efficiency and low data dependency of our algorithm, we use it for the post-training quantization, which achieves 71.27% Top-1 accuracy on MobileNetV2 with only 1.5Mb parameters.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Binarized Neural Architecture Search

Hanlin Chen
Li'an Zhuo
Baochang Zhang
Xiawu Zheng
Jianzhuang Liu
David Doermann
Rongrong Ji

Neural architecture search (NAS) can have a signiﬁcant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models. Unfortunately, this area remains largely unexplored. BNAS is more challenging than NAS due to the learning inefﬁciency caused by optimization requirements and the huge architecture space. To address these issues, we introduce channel sampling and operation space reduction into a differentiable NAS to signiﬁcantly reduce the cost of searching. This is accomplished through a performancebased strategy used to abandon less potential operations. Two optimization methods for binarized neural networks are used to validate the effectiveness of our BNAS. Extensive experiments demonstrate that the proposed BNAS achieves a performance comparable to NAS on both CIFAR and ImageNet databases. An accuracy of 96. 53% vs. 97. 22% is achieved on the CIFAR-10 dataset, but with a signiﬁcantly compressed model, and a 40% faster search than the state-of-the-art PC- DARTS.

PDF Details

AAAI Conference 2019 Conference Paper

Towards Optimal Fine Grained Retrieval via Decorrelated Centralized Loss with Normalize-Scale Layer

Xiawu Zheng
Rongrong Ji
Xiaoshuai Sun
Baochang Zhang
Yongjian Wu
Feiyue Huang

Recent advances on fine-grained image retrieval prefer learning convolutional neural network (CNN) with specific fullyconnect layer designed loss function for discriminative feature representation. Essentially, such loss should establish a robust metric to efficiently distinguish high-dimensional features within and outside fine-grained categories. To this end, the existing loss functions are defected in two aspects: (a) The feature relationship is encoded inside the training batch. Such a local scope leads to low accuracy. (b) The error is established by the mean square, which needs pairwise distance computation in training set and results in low efficiency. In this paper, we propose a novel metric learning scheme, termed Normalize-Scale Layer and Decorrelated Global Centralized Ranking Loss, which achieves extremely efficient and discriminative learning, i. e. , 5× speedup over triplet loss and 12% recall boost on CARS196. Our method originates from the classic softmax loss, which has a global structure but does not directly optimize the distance metric as well as the inter/intra class distance. We tackle this issue through a hypersphere layer and a global centralized ranking loss with a pairwise decorrelated learning. In particular, we first propose a Normalize-Scale Layer to eliminate the gap between metric distance (for measuring distance in retrieval) and dot product (for dimension reduction in classification). Second, the relationship between features is encoded under a global centralized ranking loss, which targets at optimizing metric distance globally and accelerating learning procedure. Finally, the centers are further decorrelated by Gram-Schmidt process, leading to extreme efficiency (with 20 epochs in training procedure) and discriminability in feature learning. We have conducted quantitative evaluations on two fine-grained retrieval benchmark. The superior performance demonstrates the merits of the proposed approach over the state-of-the-arts.

PDF Details

IJCAI Conference 2018 Conference Paper

Centralized Ranking Loss with Weakly Supervised Localization for Fine-Grained Object Retrieval

Xiawu Zheng
Rongrong Ji
Xiaoshuai Sun
Yongjian Wu
Feiyue Huang
Yanhua Yang

Fine-grained object retrieval has attracted extensive research focus recently. Its state-of-the-art schemesare typically based upon convolutional neural network (CNN) features. Despite the extensive progress, two issues remain open. On one hand, the deep features are coarsely extracted at image level rather than precisely at object level, which are interrupted by background clutters. On the other hand, training CNN features with a standard triplet loss is time consuming and incapable to learn discriminative features. In this paper, we present a novel fine-grained object retrieval scheme that conquers these issues in a unified framework. Firstly, we introduce a novel centralized ranking loss (CRL), which achieves a very efficient (1, 000times training speedup comparing to the triplet loss) and discriminative feature learning by a? centralized? global pooling. Secondly, a weakly supervised attractive feature extraction is proposed, which segments object contours with top-down saliency. Consequently, the contours are integrated into the CNN response map to precisely extract features? within? the target object. Interestingly, we have discovered that the combination of CRL and weakly supervised learning can reinforce each other. We evaluate the performance ofthe proposed scheme on widely-used benchmarks including CUB200-2011 and CARS196. We havereported significant gains over the state-of-the-art schemes, e. g. , 5. 4% over SCDA [Wei et al. , 2017]on CARS196, and 3. 7% on CUB200-2011.

PDF Details