Arrow Research search

Author name cluster

Xing Sun

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.

25 papers
2 author rows

Possible papers

25

AAAI Conference 2026 Conference Paper

Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving

  • Yao Cheng
  • Yibo Zhao
  • Jiapeng Zhu
  • Yao Liu
  • Xing Sun
  • Xiang Li

Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex reasoning, leading to hallucinations and unreliable outputs. Retrieval Augmented Generation (RAG) has emerged as a promising paradigm to mitigate these issues by incorporating external knowledge. Yet, conventional RAG approaches, especially those based on vector similarity, fail to effectively capture relational dependencies and support multi-step reasoning. In this work, we propose CogGRAG, a human cognition-inspired, graph-based RAG framework designed for Knowledge Graph Question Answering (KGQA). CogGRAG models the reasoning process as a tree-structured mind map that decomposes the original problem into interrelated subproblems and explicitly encodes their semantic relationships. This structure not only provides a global view to guide subsequent retrieval and reasoning but also enables self-consistent verification across reasoning paths. The framework operates in three stages: (1) top-down problem decomposition via mind map construction, (2) structured retrieval of both local and global knowledge from external Knowledge Graphs (KGs), and (3) bottom-up reasoning with dual-process self-verification. Unlike previous tree-based decomposition methods such as MindMap or Graph-CoT, CogGRAG unifies problem decomposition, knowledge retrieval, and reasoning under a single graph-structured cognitive framework, allowing early integration of relational knowledge and adaptive verification. Extensive experiments demonstrate that CogGRAG achieves superior accuracy and reliability compared to existing methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models

  • Yulei Qin
  • Gang Li
  • Zongyi Li
  • Zihan Xu
  • Yuchen Shi
  • Zhekai Lin
  • Xiao Cui
  • Ke Li

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabilities of LLMs. However, we find that the vanilla CoT exerts a negative impact on performance due to its superficial reasoning pattern of simply paraphrasing the instructions. It fails to peel back the compositions of constraints for identifying their relationship across hierarchies of types and dimensions. To this end, we propose RAIF, a systematic method to boost LLMs in dealing with complex instructions via incentivizing reasoning for test-time compute scaling. First, we stem from the decomposition of complex instructions under existing taxonomies and propose a reproducible data acquisition method. Second, we exploit reinforcement learning (RL) with verifiable rule-centric reward signals to cultivate reasoning specifically for instruction following. We address the shallow, non-essential nature of reasoning under complex instructions via sample-wise contrast for superior CoT enforcement. We also exploit behavior cloning of experts to facilitate steady distribution shift from fast-thinking LLMs to skillful reasoners. Extensive evaluations on seven comprehensive benchmarks confirm the validity of the proposed method, where a 1. 5B LLM achieves 11. 74% gains with performance comparable to a 8B LLM. Evaluation on OOD constraints also confirms the generalizability of our RAIF.

PDF Details

NeurIPS Conference 2025 Conference Paper

LTD-Bench: Evaluating Large Language Models by Letting Them Draw

  • Liuhao Lin
  • Ke Li
  • Zihan Xu
  • Yuchen Shi
  • Yulei Qin
  • Yan Zhang
  • Xing Sun
  • Rongrong Ji

Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research—relying on opaque numerical metrics that conceal fundamental limitations in spatial reasoning while providing no intuitive understanding of model capabilities. This deficiency creates a dangerous disconnect between reported performance and practical abilities, particularly for applications requiring physical world understanding. We introduce LTD-Bench, a breakthrough benchmark that transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code. This approach makes spatial reasoning limitations immediately apparent even to non-experts, bridging the fundamental gap between statistical performance and intuitive assessment. LTD-Bench implements a comprehensive methodology with complementary generation tasks (testing spatial imagination) and recognition tasks (assessing spatial perception) across three progressively challenging difficulty levels, methodically evaluating both directions of the critical language-spatial mapping. Our extensive experiments with state-of-the-art models expose an alarming capability gap: even LLMs achieving impressive results on traditional benchmarks demonstrate profound deficiencies in establishing bidirectional mappings between language and spatial concepts—a fundamental limitation that undermines their potential as genuine world models. Furthermore, LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity. Our dataset and codes are available at https: //github. com/walktaster/LTD-Bench.

PDF 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

AAAI Conference 2025 Conference Paper

Probability-Density-aware Semi-supervised Learning

  • Shuyang Liu
  • Ruiqiu Zheng
  • Yunhang Shen
  • Zhou Yu
  • Ke Li
  • Xing Sun
  • Shaohui Lin

In Semi-supervised learning(SSL), we always accept cluster assumption, assuming features in different high-density regions belong to other categories. However, it is always ignored by existing algorithms and needs mathematical explanations. This paper first proposes a theorem to statistically explain cluster assumption and prove that the probability density can significantly help to use the prior fully. A Probability-Density-Aware Measure(PM) is proposed based on the theorem to discern the similarity between neighbor points. The PM is deployed to improve Label Propagation and a new pseudo-labeling algorithm, the Probability-Density-Aware Label Propagation(PMLP), is proposed. We also prove that traditional first-order similarity pseudo-labeling could be viewed as a particular case of PMLP, which provides a comprehensive theoretical understanding of PMLP's superior performance. Extensive experiments demonstrate that PMLP achieves outstanding performance compared with other recent methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup

  • Fanxu Meng
  • Pingzhi Tang
  • Zengwei Yao
  • Xing Sun
  • Muhan Zhang

Modern large-language models often face communication bottlenecks on current hardware rather than computational limitations. Multi-head latent attention (MLA) addresses this by compressing the key-value cache using low-rank matrices, while the Absorb operation prevents the KV cache from reverting to its original size, significantly boosting both training and inference speed. Despite the success of DeepSeek V2/V3/R1, most model providers have heavily invested in optimizing GQA-based models and, therefore, lack strong incentives to retrain MLA-based models from scratch. This paper demonstrates that MLA provides superior expressive power compared to GQA with the same KV cache overhead, thereby offering a rationale for transitioning from GQA to MLA. In addition, we introduce TransMLA, a framework that seamlessly converts any GQA-based pre-trained model (e. g. , LLaMA, Qwen, Gemma, Mistral/Mixtral) into an MLA-based model. For the first time, our method enables direct conversion of these models into a format compatible with DeepSeek's codebase, allowing them to fully leverage the existing, highly-optimized support for the DeepSeek architecture within inference engines like vLLM and SGlang. By compressing 93\% of the KV cache in LLaMA-2-7B, we achieve a 10x speedup with an 8K context length while maintaining meaningful output. Moreover, the model requires only 6B tokens for fine-tuning to recover comparable performance across multiple benchmarks. TransMLA provides a practical path for migrating GQA-based models to the MLA structure, and when combined with DeepSeek’s advanced optimizations—such as FP8 quantization and Multi-Token Prediction—further inference acceleration can be achieved.

PDF Details

TMLR Journal 2025 Journal Article

Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models

  • Yulei Qin
  • Yuncheng Yang
  • Pengcheng Guo
  • Gang Li
  • Hang Shao
  • Yuchen Shi
  • Zihan Xu
  • Yun Gu

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and practical. To pinpoint the most beneficial datapoints, data assessment and selection methods have been proposed in the fields of natural language processing (NLP) and deep learning. However, under the context of instruction tuning, there still exists a gap in knowledge on what kind of data evaluation metrics can be employed and how they can be integrated into the selection mechanism. To bridge this gap, we present a comprehensive review on existing literature of data assessment and selection especially for instruction tuning of LLMs. We systematically categorize all applicable methods into quality-based, diversity-based, and importance-based ones where a unified, fine-grained taxonomy is structured. For each category, representative methods are elaborated to describe the landscape of relevant research. In addition, comparison between the latest methods is conducted on their officially reported results to provide in-depth discussions on their limitations. Finally, we summarize the open challenges and propose the promosing avenues for future studies. All related contents are available at https://github.com/yuleiqin/fantastic-data-engineering.

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

VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model

  • Zuwei Long
  • Yunhang Shen
  • Chaoyou Fu
  • Heting Gao
  • Lijiang Li
  • Peixian Chen
  • Mengdan Zhang
  • Hang Shao

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience high latency when generating the first audio token during streaming, which poses a significant bottleneck for deployment. To address this issue, we propose VITA-Audio, an end-to-end large speech model with fast audio-text token generation. Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios. In addition, a four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality. To our knowledge, VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency. VITA-Audio is fully reproducible and is trained on open-source data only. Experimental results demonstrate that our model achieves an inference speedup of 3~5x at the 7B parameter scale, but also significantly outperforms open-source models of similar model size on multiple benchmarks for automatic speech recognition (ASR), text-to-speech (TTS), and spoken question answering (SQA) tasks.

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

AAAI Conference 2024 Conference Paper

Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation

  • Hao Liu
  • Xin Li
  • Mingming Gong
  • Bing Liu
  • Yunfei Wu
  • Deqiang Jiang
  • Yinsong Liu
  • Xing Sun

Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community. While impressive success, most single table component-based methods can not perform well on unregularized table cases distracted by not only complicated inner structure but also exterior capture distortion. In this paper, we raise it as Complex TSR problem, where the performance degeneration of existing methods is attributable to their inefficient component usage and redundant post-processing. To mitigate it, we shift our perspective from table component extraction towards the efficient multiple components leverage, which awaits further exploration in the field. Specifically, we propose a seminal method, termed GrabTab, equipped with newly proposed Component Deliberator, to handle various types of tables in a unified framework. Thanks to its progressive deliberation mechanism, our GrabTab can flexibly accommodate to most complex tables with reasonable components selected but without complicated post-processing involved. Quantitative experimental results on public benchmarks demonstrate that our method significantly outperforms the state-of-the-arts, especially under more challenging scenes.

PDF Details DOI

AAAI Conference 2024 Conference Paper

SoftCLIP: Softer Cross-Modal Alignment Makes CLIP Stronger

  • Yuting Gao
  • Jinfeng Liu
  • Zihan Xu
  • Tong Wu
  • Enwei Zhang
  • Ke Li
  • Jie Yang
  • Wei Liu

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challenging task, and noise exists in the commonly used datasets. To address this issue, we propose SoftCLIP, a novel approach that relaxes the strict one-to-one constraint and achieves a soft cross-modal alignment by introducing a softened target, which is generated from the fine-grained intra-modal self-similarity. The intra-modal guidance is indicative to enable two pairs have some local similarities and model many-to-many relationships between the two modalities. Besides, since the positive still dominates in the softened target distribution, we disentangle the negatives in the distribution to further boost the relation alignment with the negatives in the cross-modal learning. Extensive experiments demonstrate the effectiveness of SoftCLIP. In particular, on ImageNet zero-shot classification task, using CC3M/CC12M as pre-training dataset, SoftCLIP brings a top-1 accuracy improvement of 6.8%/7.2% over the CLIP baseline.

PDF Details DOI

AAAI Conference 2024 Conference Paper

SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space

  • Yunchen Li
  • Zhou Yu
  • Gaoqi He
  • Yunhang Shen
  • Ke Li
  • Xing Sun
  • Shaohui Lin

Symmetric positive definite(SPD) matrices have shown important value and applications in statistics and machine learning, such as FMRI analysis and traffic prediction. Previous works on SPD matrices mostly focus on discriminative models, where predictions are made directly on E(X|y), where y is a vector and X is an SPD matrix. However, these methods are challenging to handle for large-scale data. In this paper, inspired by denoising diffusion probabilistic model(DDPM), we propose a novel generative model, termed SPD-DDPM, by introducing Gaussian distribution in the SPD space to estimate E(X|y). Moreover, our model can estimate p(X) unconditionally and flexibly without giving y. On the one hand, the model conditionally learns p(X|y) and utilizes the mean of samples to obtain E(X|y) as a prediction. On the other hand, the model unconditionally learns the probability distribution of the data p(X) and generates samples that conform to this distribution. Furthermore, we propose a new SPD net which is much deeper than the previous networks and allows for the inclusion of conditional factors. Experiment results on toy data and real taxi data demonstrate that our models effectively fit the data distribution both unconditionally and conditionally.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Visual Hallucination Elevates Speech Recognition

  • Fang Zhang
  • Yongxin Zhu
  • Xiangxiang Wang
  • Huang Chen
  • Xing Sun
  • Linli Xu

Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and visual video signals. Although existing methods have demonstrated that the aligned visual input of lip movements can enhance the robustness of AVSR systems against noise, the paired videos are not always available during inference, leading to the problem of the missing visual modality, which restricts their practicality in real-world scenarios. To tackle this problem, we propose a Discrete Feature based Visual Generative Model (DFVGM) which exploits semantic correspondences between the audio and visual modalities during training, generating visual hallucinations in lieu of real videos during inference. To achieve that, the primary challenge is to generate the visual hallucination given the noisy audio while preserving semantic correspondences with the clean speech. To tackle this challenge, we start with training the audio encoder in the Audio-Only (AO) setting, which generates continuous semantic features closely associated with the linguistic information. Simultaneously, the visual encoder is trained in the Visual-Only (VO) setting, producing visual features that are phonetically related. Next, we employ K-means to discretize the continuous audio and visual feature spaces. The discretization step allows DFVGM to capture high-level semantic structures that are more resilient to noise and generate visual hallucinations with high quality. To evaluate the effectiveness and robustness of our approach, we conduct extensive experiments on two publicly available datasets. The results demonstrate that our method achieves a remarkable 53% relative reduction (30.5%->12.9%) in Word Error Rate (WER) on average compared to the current state-of-the-art Audio-Only (AO) baselines while maintaining comparable results (< 5% difference) under the Audio-Visual (AV) setting even without video as input.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes

  • Yulei Qin
  • Xingyu Chen
  • Yunhang Shen
  • Chaoyou Fu
  • Yun Gu
  • Ke Li
  • Xing Sun
  • Rongrong Ji

Webly supervised learning has attracted increasing attention for its effectiveness in exploring publicly accessible data at scale without manual annotation. However, most existing methods of learning with web datasets are faced with challenges from label noise, and they have limited assumptions on clean samples under various noise. For instance, web images retrieved with queries of ”tiger cat“ (a cat species) and ”drumstick“ (a musical instrument) are almost dominated by images of tigers and chickens, which exacerbates the challenge of fine-grained visual concept learning. In this case, exploiting both web images and their associated texts is a requisite solution to combat real-world noise. In this paper, we propose Cross-modality Aligned Prototypes (CAPro), a unified prototypical contrastive learning framework to learn visual representations with correct semantics. For one thing, we leverage textual prototypes, which stem from the distinct concept definition of classes, to select clean images by text matching and thus disambiguate the formation of visual prototypes. For another, to handle missing and mismatched noisy texts, we resort to the visual feature space to complete and enhance individual texts and thereafter improve text matching. Such semantically aligned visual prototypes are further polished up with high-quality samples, and engaged in both cluster regularization and noise removal. Besides, we propose collective bootstrapping to encourage smoother and wiser label reference from appearance-similar instances in a manner of dictionary look-up. Extensive experiments on WebVision1k and NUS-WIDE (Web) demonstrate that CAPro well handles realistic noise under both single-label and multi-label scenarios. CAPro achieves new state-of-the-art performance and exhibits robustness to open-set recognition. Codes are available at https: //github. com/yuleiqin/capro.

PDF Details

ICLR Conference 2022 Conference Paper

AS-MLP: An Axial Shifted MLP Architecture for Vision

  • Dongze Lian
  • Zehao Yu 0002
  • Xing Sun
  • Shenghua Gao

An Axial Shifted MLP architecture (AS-MLP) is proposed in this paper. Different from MLP-Mixer, where the global spatial feature is encoded for information flow through matrix transposition and one token-mixing MLP, we pay more attention to the local features interaction. By axially shifting channels of the feature map, AS-MLP is able to obtain the information flow from different axial directions, which captures the local dependencies. Such an operation enables us to utilize a pure MLP architecture to achieve the same local receptive field as CNN-like architecture. We can also design the receptive field size and dilation of blocks of AS-MLP, \emph{etc}, in the same spirit of convolutional neural networks. With the proposed AS-MLP architecture, our model obtains 83.3\% Top-1 accuracy with 88M parameters and 15.2 GFLOPs on the ImageNet-1K dataset. Such a simple yet effective architecture outperforms all MLP-based architectures and achieves competitive performance compared to the transformer-based architectures (\emph{e.g.}, Swin Transformer) even with slightly lower FLOPs. In addition, AS-MLP is also the first MLP-based architecture to be applied to the downstream tasks (\emph{e.g.}, object detection and semantic segmentation). The experimental results are also impressive. Our proposed AS-MLP obtains 51.5 mAP on the COCO validation set and 49.5 MS mIoU on the ADE20K dataset, which is competitive compared to the transformer-based architectures. Our AS-MLP establishes a strong baseline of MLP-based architecture. Code is available at \url{https://github.com/svip-lab/AS-MLP}.

Details

AAAI Conference 2022 Conference Paper

Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

  • Yifan Xu
  • Zhijie Zhang
  • Mengdan Zhang
  • Kekai Sheng
  • Ke Li
  • Weiming Dong
  • Liqing Zhang
  • Changsheng Xu

Vision transformers (ViTs) have attracted considerable research attention recently, but the huge computational cost is still a severe issue. A mainstream paradigm for computation reduction aims to reduce the number of tokens given that the computation complexity of ViT is quadratic with respect to the input sequence length. Existing designs include structured spatial compression that uses a progressive shrinking pyramid to reduce the computations of large feature maps, and unstructured token pruning that dynamically drops redundant tokens. However, limitations of existing token pruning lie in the following aspects: 1) the incomplete spatial structure caused by pruning is incompatible with structured spatial compression that is commonly used in modern deep-narrow transformers; 2) it usually requires a time-consuming pretraining procedure. To address the limitations and expand the applicable scenario of token pruning, we present Evo-ViT, a self-motivated slow-fast token evolution approach for vision transformers. Specifically, we conduct unstructured instancewise token selection by taking advantage of the simple and effective global class attention that is native to vision transformers. Then, we propose to update the selected informative tokens and uninformative tokens with different computation paths, namely, slow-fast updating. Since slow-fast updating mechanism maintains the spatial structure and information flow, Evo-ViT can accelerate vanilla transformers of both flat and deep-narrow structures from the very beginning of the training process. Experimental results demonstrated that our method significantly reduces the computational cost of vision transformers while maintaining comparable performance on image classification. For example, our method accelerates DeiT-S by over 60% throughput while only sacrificing 0. 4% top-1 accuracy on ImageNet-1K, outperforming current token pruning methods on both accuracy and efficiency.

PDF Details

IJCAI Conference 2021 Conference Paper

Dig into Multi-modal Cues for Video Retrieval with Hierarchical Alignment

  • Wenzhe Wang
  • Mengdan Zhang
  • Runnan Chen
  • Guanyu Cai
  • Penghao Zhou
  • Pai Peng
  • Xiaowei Guo
  • Jian Wu

Multi-modal cues presented in videos are usually beneficial for the challenging video-text retrieval task on internet-scale datasets. Recent video retrieval methods take advantage of multi-modal cues by aggregating them to holistic high-level semantics for matching with text representations in a global view. In contrast to this global alignment, the local alignment of detailed semantics encoded within both multi-modal cues and distinct phrases is still not well conducted. Thus, in this paper, we leverage the hierarchical video-text alignment to fully explore the detailed diverse characteristics in multi-modal cues for fine-grained alignment with local semantics from phrases, as well as to capture a high-level semantic correspondence. Specifically, multi-step attention is learned for progressively comprehensive local alignment and a holistic transformer is utilized to summarize multi-modal cues for global alignment. With hierarchical alignment, our model outperforms state-of-the-art methods on three public video retrieval datasets.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion

  • Jinpeng Wang
  • Yuting Gao
  • Ke Li
  • Jianguo Hu
  • Xinyang Jiang
  • Xiaowei Guo
  • Rongrong Ji
  • Xing Sun

One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action categories are highly related with the scene where the action happens, making the model tend to degrade to a solution where only the scene information is encoded. For example, a trained model may predict a video as playing football simply because it sees the field, neglecting that the subject is dancing as a cheerleader on the field. This is against our original intention towards the video representation learning and may bring scene bias on a different dataset that can not be ignored. In order to tackle this problem, we propose to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid. Specifically, we construct a positive clip and a negative clip for each video. Compared to the original video, the positive/negative is motion-untouched/broken but scenebroken/untouched by Spatial Local Disturbance and Temporal Local Disturbance. Our objective is to pull the positive closer while pushing the negative farther to the original clip in the latent space. In this way, the impact of the scene is weakened while the temporal sensitivity of the network is further enhanced. We conduct experiments on two tasks with various backbones and different pre-training datasets, and find that our method surpass the SOTA methods with a remarkable 8. 1% and 8. 8% improvement towards action recognition task on the UCF101 and HMDB51 datasets respectively using the same backbone.

PDF Details

AAAI Conference 2021 Conference Paper

One for More: Selecting Generalizable Samples for Generalizable ReID Model

  • Enwei Zhang
  • Xinyang Jiang
  • Hao Cheng
  • Ancong Wu
  • Fufu Yu
  • Ke Li
  • Xiaowei Guo
  • Feng Zheng

Current training objectives of existing person Re- IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch. It will inevitably cause the model to over-fit the data in the dominant position (e. g. , head data in imbalanced class, easy samples or noisy samples). The latest resampling methods address the issue by designing specific criterion to select specific samples that trains the model generalize more on certain type of data (e. g. , hard samples, tail data), which is not adaptive to the inconsistent real world ReID data distributions. Therefore, instead of simply presuming on what samples are generalizable, this paper proposes a one-for-more training objective that directly takes the generalization ability of selected samples as a loss function and learn a sampler to automatically select generalizable samples. More importantly, our proposed one-for-more based sampler can be seamlessly integrated into the ReID training framework which is able to simultaneously train ReID models and the sampler in an end-to-end fashion. The experimental results show that our method can effectively improve the ReID model training and boost the performance of ReID models.

PDF Details

AAAI Conference 2020 Conference Paper

Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification

  • Fengxiang Yang
  • Ke Li
  • Zhun Zhong
  • Zhiming Luo
  • Xing Sun
  • Hao Cheng
  • Xiaowei Guo
  • Feiyue Huang

Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i. e. , source domain, few works can generalize well on the unseen target domain. One popular solution is assigning unlabeled target images with pseudo labels by clustering, and then retraining the model. However, clustering methods tend to introduce noisy labels and discard low confidence samples as outliers, which may hinder the retraining process and thus limit the generalization ability. In this study, we argue that by explicitly adding a sample filtering procedure after the clustering, the mined examples can be much more efficiently used. To this end, we design an asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other. Meanwhile, one of the models receives samples as pure as possible, while the other takes in samples as diverse as possible. This procedure encourages that the selected training samples can be both clean and miscellaneous, and that the two models can promote each other iteratively. Extensive experiments show that the proposed framework can consistently benefit most clustering based methods, and boost the state-of-the-art adaptation accuracy. Our code is available at https: //github. com/FlyingRoastDuck/ACT AAAI20.

PDF Details

NeurIPS Conference 2020 Conference Paper

Pruning Filter in Filter

  • Fanxu Meng
  • Hao Cheng
  • Ke Li
  • Huixiang Luo
  • Xiaowei Guo
  • Guangming Lu
  • Xing Sun

Pruning has become a very powerful and effective technique to compress and accelerate modern neural networks. Existing pruning methods can be grouped into two categories: filter pruning (FP) and weight pruning (WP). FP wins at hardware compatibility but loses at the compression ratio compared with WP. To converge the strength of both methods, we propose to prune the filter in the filter. Specifically, we treat a filter F, whose size is C K K, as K K stripes, i. e. , 1 1 filters, then by pruning the stripes instead of the whole filter, we can achieves finer granularity than traditional FP while being hardware friendly. We term our method as SWP (Stripe-Wise Pruning). SWP is implemented by introducing a novel learnable matrix called Filter Skeleton, whose values reflect the optimal shape of each filter. As some recent work has shown that the pruned architecture is more crucial than the inherited important weights, we argue that the architecture of a single filter, i. e. , the Filter Skeleton, also matters. Through extensive experiments, we demonstrate that SWP is more effective compared to the previous FP-based methods and achieves the state-of-art pruning ratio on CIFAR-10 and ImageNet datasets without obvious accuracy drop.

PDF Details

AAAI Conference 2020 Conference Paper

Rethinking Temporal Fusion for Video-Based Person Re-Identification on Semantic and Time Aspect

  • Xinyang Jiang
  • Yifei Gong
  • Xiaowei Guo
  • Qize Yang
  • Feiyue Huang
  • Wei-Shi Zheng
  • Feng Zheng
  • Xing Sun

Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video. However, existing video-based ReID methods do not consider the semantic difference brought by the outputs of different network stages, which potentially compromises the information richness of the person features. Furthermore, traditional methods ignore important relationship among frames, which causes information redundancy in fusion along the time axis. To address these issues, we propose a novel general temporal fusion framework to aggregate frame features on both semantic aspect and time aspect. As for the semantic aspect, a multi-stage fusion network is explored to fuse richer frame features at multiple semantic levels, which can effectively reduce the information loss caused by the traditional single-stage fusion. While, for the time axis, the existing intra-frame attention method is improved by adding a novel inter-frame attention module, which effectively reduces the information redundancy in temporal fusion by taking the relationship among frames into consideration. The experimental results show that our approach can effectively improve the video-based re-identification accuracy, achieving the state-of-the-art performance.

PDF Details

AAAI Conference 2020 Conference Paper

Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification

  • Zhihui Zhu
  • Xinyang Jiang
  • Feng Zheng
  • Xiaowei Guo
  • Feiyue Huang
  • Xing Sun
  • Weishi Zheng

Although great progress in supervised person reidentification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called Viewpoint-Aware Loss with Angular Regularization (VA-reID). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.

PDF Details

JMLR Journal 2008 Journal Article

On the Size and Recovery of Submatrices of Ones in a Random Binary Matrix

  • Xing Sun
  • Andrew B. Nobel

Binary matrices, and their associated submatrices of 1s, play a central role in the study of random bipartite graphs and in core data mining problems such as frequent itemset mining (FIM). Motivated by these connections, this paper addresses several statistical questions regarding submatrices of 1s in a random binary matrix with independent Bernoulli entries. We establish a three-point concentration result, and a related probability bound, for the size of the largest square submatrix of 1s in a square Bernoulli matrix, and extend these results to non-square matrices and submatrices with fixed aspect ratios. We then consider the noise sensitivity of frequent itemset mining under a simple binary additive noise model, and show that, even at small noise levels, large blocks of 1s leave behind fragments of only logarithmic size. As a result, standard FIM algorithms, which search only for submatrices of 1s, cannot directly recover such blocks when noise is present. On the positive side, we show that an error-tolerant frequent itemset criterion can recover a submatrix of 1s against a background of 0s plus noise, even when the size of the submatrix of 1s is very small. [abs] [ pdf ][ bib ] &copy JMLR 2008. ( edit, beta )

PDF Details