Jiahuan Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jiahuan Zhou has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
- Yuxin Peng
Peking University, Beijing, China
23 shared publications - Xu Zou
Huazhong University of Science and Technology
14 shared publications - Sheng Zhong
Huazhong University of Science and Technology
9 shared publications - Luxin Yan
Huazhong University of Science and Technology
8 shared publications - Zhenyu Cui
Wangxuan Institute of Computer Technology, Peking University, Beijing, China
8 shared publications Zichen Liu
Wangxuan Institute of Computer Technology Peking University 100871 Beijing China
6 shared publications
Latest Publications
- 11 September 2026
- Published by Springer Nature
- p. 93-110
SCORE: SubDistribution-Aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-identification
- 11 September 2026
- Published by Springer Nature
- p. 93-110
SCORE: SubDistribution-Aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-identification
- 11 September 2026
- Published by Springer Nature
- p. 147-164
DG-Force: Disentangling and Gathering Forensic Cues is Needed for Image Manipulation Localization
- 11 September 2026
- Published by Springer Nature
- p. 147-164
DG-Force: Disentangling and Gathering Forensic Cues is Needed for Image Manipulation Localization
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Mitigate Catastrophic Remembering via Continual Self-Paced Dual-Knowledge Purification for Noisy Lifelong Person Re-Identification
Current Lifelong Person Re-Identification (LReID) methods focus on tackling the data streams with accurate labels. When the data streams with noisy labels are given, their performance is severely degraded since the model continually remembers erroneous knowledge induced by the label noise. Moreover, the well-known issue of catastrophic forgetting in LReID is exacerbated by noisy labels, which disrupt the retention of correct knowledge from previous models. Such a practical Noisy LReID task is important but challenging, and few works have attempted to address it. In this paper, we pioneer the investigation of Noisy LReID and propose a Continual Self-Paced Dual-Knowledge Purification (CSDP) method to address the catastrophic remembering of erroneous knowledge, catastrophic forgetting of correct knowledge, and limited acquisition capacity, simultaneously. Specifically, both local distribution information and global classification results are jointly leveraged to enhance the recognition and correction of noisy labels. In addition, a self-paced learning paradigm is introduced to facilitate the progressive accumulation of reliable knowledge. Finally, a Noisy LReID benchmark is constructed to support research on this task. Extensive experimental results demonstrate that the proposed CSDP method, under comparable computational overhead, outperforms state-of-the-art methods by a large margin. Our code is available at https://github.com/zhoujiahuan1991/TPAMI-CSDP
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Mitigate Catastrophic Remembering via Continual Self-Paced Dual-Knowledge Purification for Noisy Lifelong Person Re-Identification
Current Lifelong Person Re-Identification (LReID) methods focus on tackling the data streams with accurate labels. When the data streams with noisy labels are given, their performance is severely degraded since the model continually remembers erroneous knowledge induced by the label noise. Moreover, the well-known issue of catastrophic forgetting in LReID is exacerbated by noisy labels, which disrupt the retention of correct knowledge from previous models. Such a practical Noisy LReID task is important but challenging, and few works have attempted to address it. In this paper, we pioneer the investigation of Noisy LReID and propose a Continual Self-Paced Dual-Knowledge Purification (CSDP) method to address the catastrophic remembering of erroneous knowledge, catastrophic forgetting of correct knowledge, and limited acquisition capacity, simultaneously. Specifically, both local distribution information and global classification results are jointly leveraged to enhance the recognition and correction of noisy labels. In addition, a self-paced learning paradigm is introduced to facilitate the progressive accumulation of reliable knowledge. Finally, a Noisy LReID benchmark is constructed to support research on this task. Extensive experimental results demonstrate that the proposed CSDP method, under comparable computational overhead, outperforms state-of-the-art methods by a large margin. Our code is available at https://github.com/zhoujiahuan1991/TPAMI-CSDP
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (4) , 4570-4586
Bi-C 2 R: Bidirectional Continual Compatible Representation for Re-Indexing Free Lifelong Person Re-Identification
Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performance of all data. Its main challenge is to avoid the catastrophic forgetting problem of old knowledge while training on new data. Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as “re-indexing”. However, historical gallery data typically suffers from direct saving due to the data privacy issue and the high re-indexing costs for large-scale gallery images. As a result, it inevitably leads to incompatible retrieval between query features extracted by the updated model and gallery features extracted by those before the update, greatly impairing the re-identification performance. To tackle the above issue, this paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images. Therefore, RFL-ReID is more challenging than L-ReID, requiring continuous learning and balancing new and old knowledge in diverse streaming data, and making the features output by the new and old models compatible with each other. To this end, we propose a Bidirectional Continuous Compatible Representation (Bi-C$^{2}$ R) framework to continuously update the gallery features extracted by the old model to perform efficient L-ReID in a compatible manner. Specifically, a bidirectional compatible transfer network is first designed to bridge the relationship between new and old knowledge and continuously update the old gallery features to the new feature space after the updating. Secondly, a bidirectional compatible distillation module and a bidirectional anti-forgetting distillation model are designed to balance the compatibility between the new and old knowledge in dual feature spaces. Finally, a feature-level exponential moving average strategy is designed to adaptively fill the diverse knowledge gaps between different data domains. Finally, we verify our proposed Bi-C$^{2}$ R method through theoretical analysis and extensive experiments on multiple benchmarks, which demonstrate that the proposed method can achieve leading performance on both the introduced RFL-ReID task and the traditional L-ReID task.- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (4) , 4570-4586
Bi-C 2 R: Bidirectional Continual Compatible Representation for Re-Indexing Free Lifelong Person Re-Identification
Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performance of all data. Its main challenge is to avoid the catastrophic forgetting problem of old knowledge while training on new data. Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as “re-indexing”. However, historical gallery data typically suffers from direct saving due to the data privacy issue and the high re-indexing costs for large-scale gallery images. As a result, it inevitably leads to incompatible retrieval between query features extracted by the updated model and gallery features extracted by those before the update, greatly impairing the re-identification performance. To tackle the above issue, this paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images. Therefore, RFL-ReID is more challenging than L-ReID, requiring continuous learning and balancing new and old knowledge in diverse streaming data, and making the features output by the new and old models compatible with each other. To this end, we propose a Bidirectional Continuous Compatible Representation (Bi-C$^{2}$ R) framework to continuously update the gallery features extracted by the old model to perform efficient L-ReID in a compatible manner. Specifically, a bidirectional compatible transfer network is first designed to bridge the relationship between new and old knowledge and continuously update the old gallery features to the new feature space after the updating. Secondly, a bidirectional compatible distillation module and a bidirectional anti-forgetting distillation model are designed to balance the compatibility between the new and old knowledge in dual feature spaces. Finally, a feature-level exponential moving average strategy is designed to adaptively fill the diverse knowledge gaps between different data domains. Finally, we verify our proposed Bi-C$^{2}$ R method through theoretical analysis and extensive experiments on multiple benchmarks, which demonstrate that the proposed method can achieve leading performance on both the introduced RFL-ReID task and the traditional L-ReID task.- 15 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
Supervisory feedback for high-resolution low-textured large-scale multi-view stereo
- 15 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
Supervisory feedback for high-resolution low-textured large-scale multi-view stereo
- Open Access
CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification
Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matching across day and night, Visible-Infrared Lifelong person Re-IDentification (VI-LReID) focuses on sequential training on data from visible and infrared modalities and pursues average performance over all data. To this end, existing methods typically exploit cross-modal knowledge distillation to alleviate the catastrophic forgetting of old knowledge. However, these methods ignore the mutual interference of modality-specific knowledge acquisition and modality-common knowledge anti-forgetting, where conflicting knowledge leads to collaborative forgetting. To address the above problems, this paper proposes a Cross-modality Knowledge Disentanglement and Alignment method, called CKDA, which explicitly separates and preserves modality-specific knowledge and modality-common knowledge in a balanced way. Specifically, a Modality-Common Prompting (MCP) module and a Modality-Specific Prompting (MSP) module are proposed to explicitly disentangle and purify discriminative information that coexists and is specific to different modalities, avoiding the mutual interference between both knowledge. In addition, a Cross-modal Knowledge Alignment (CKA) module is designed to further align the disentangled new knowledge with the old one in two mutually independent inter- and intra-modality feature spaces based on dual-modality prototypes in a balanced manner. Extensive experiments on four benchmark datasets verify the effectiveness and superiority of our CKDA against state-of-the-art methods. The source code of this paper is available at https://github.com/PKU-ICST-MIPL/CKDA-AAAI2026.
Open AccessCKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification
Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matching across day and night, Visible-Infrared Lifelong person Re-IDentification (VI-LReID) focuses on sequential training on data from visible and infrared modalities and pursues average performance over all data. To this end, existing methods typically exploit cross-modal knowledge distillation to alleviate the catastrophic forgetting of old knowledge. However, these methods ignore the mutual interference of modality-specific knowledge acquisition and modality-common knowledge anti-forgetting, where conflicting knowledge leads to collaborative forgetting. To address the above problems, this paper proposes a Cross-modality Knowledge Disentanglement and Alignment method, called CKDA, which explicitly separates and preserves modality-specific knowledge and modality-common knowledge in a balanced way. Specifically, a Modality-Common Prompting (MCP) module and a Modality-Specific Prompting (MSP) module are proposed to explicitly disentangle and purify discriminative information that coexists and is specific to different modalities, avoiding the mutual interference between both knowledge. In addition, a Cross-modal Knowledge Alignment (CKA) module is designed to further align the disentangled new knowledge with the old one in two mutually independent inter- and intra-modality feature spaces based on dual-modality prototypes in a balanced manner. Extensive experiments on four benchmark datasets verify the effectiveness and superiority of our CKDA against state-of-the-art methods. The source code of this paper is available at https://github.com/PKU-ICST-MIPL/CKDA-AAAI2026.
- Open Access
State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
Recently, pre-trained state space models have shown great potential for video classification, which sequentially compresses visual tokens in videos with linear complexity, thereby improving the processing efficiency of video data while maintaining high performance. To apply powerful pre-trained models to downstream tasks, prompt learning is proposed to achieve efficient downstream task adaptation with only a small number of fine-tuned parameters. However, the sequentially compressed visual prompt tokens fail to capture the spatial and temporal contextual information in the video, thus limiting the effective propagation of spatial information within a video frame and temporal information between frames in the state compression model and the extraction of discriminative information. To tackle the above issue, we proposed a State Space Prompting (SSP) method for video understanding, which combines intra-frame and inter-frame prompts to aggregate and propagate key spatiotemporal information in the video. Specifically, an Intra-Frame Gathering (IFG) module is designed to aggregate spatial key information within each frame. Besides, an Inter-Frame Spreading (IFS) module is designed to spread discriminative spatio-temporal information across different frames. By adaptively balancing and compressing key spatio-temporal information within and between frames, our SSP effectively propagates discriminative information in videos in a complementary manner. Extensive experiments on four video benchmark datasets verify that our SSP significantly outperforms existing SOTA methods by 2.76% on average while reducing the overhead of fine-tuning parameters.
Open AccessState Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
Recently, pre-trained state space models have shown great potential for video classification, which sequentially compresses visual tokens in videos with linear complexity, thereby improving the processing efficiency of video data while maintaining high performance. To apply powerful pre-trained models to downstream tasks, prompt learning is proposed to achieve efficient downstream task adaptation with only a small number of fine-tuned parameters. However, the sequentially compressed visual prompt tokens fail to capture the spatial and temporal contextual information in the video, thus limiting the effective propagation of spatial information within a video frame and temporal information between frames in the state compression model and the extraction of discriminative information. To tackle the above issue, we proposed a State Space Prompting (SSP) method for video understanding, which combines intra-frame and inter-frame prompts to aggregate and propagate key spatiotemporal information in the video. Specifically, an Intra-Frame Gathering (IFG) module is designed to aggregate spatial key information within each frame. Besides, an Inter-Frame Spreading (IFS) module is designed to spread discriminative spatio-temporal information across different frames. By adaptively balancing and compressing key spatio-temporal information within and between frames, our SSP effectively propagates discriminative information in videos in a complementary manner. Extensive experiments on four video benchmark datasets verify that our SSP significantly outperforms existing SOTA methods by 2.76% on average while reducing the overhead of fine-tuning parameters.
- Open Access
Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre-acquiring downstream domain data. To this end, existing advanced CTTA methods mainly reduce the catastrophic forgetting of historical knowledge caused by irregular switching of downstream domain data by restoring the initial model or reusing historical models. However, these methods are usually accompanied by serious insufficient learning of new knowledge and interference from potentially harmful historical knowledge, resulting in severe performance degradation. To this end, we propose a class-aware domain Knowledge Fusion and Fission method for continual test-time adaptation, called KFF, which adaptively expands and merges class-aware domain knowledge in old and new domains according to the test-time data from different domains, where discriminative historical knowledge can be dynamically accumulated. Specifically, considering the huge domain gap within streaming data, a domain Knowledge FIssion (KFI) module is designed to adaptively separate new domain knowledge from a paired class-aware domain prompt pool, alleviating the impact of negative knowledge brought by old domains that are distinct from the current domain. Besides, to avoid the cumulative computation and storage overheads from continuously fissioning new knowledge, a domain Knowledge FUsion (KFU) module is further designed to merge the fissioned new knowledge into the existing knowledge pool with minimal cost, where a greedy knowledge dynamic merging strategy is designed to improve the compatibility of new and old knowledge while keeping the computational efficiency. Extensive experiments on the ImageNet-C dataset verify the effectiveness of our proposed method against other methods.
Open AccessClass-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre-acquiring downstream domain data. To this end, existing advanced CTTA methods mainly reduce the catastrophic forgetting of historical knowledge caused by irregular switching of downstream domain data by restoring the initial model or reusing historical models. However, these methods are usually accompanied by serious insufficient learning of new knowledge and interference from potentially harmful historical knowledge, resulting in severe performance degradation. To this end, we propose a class-aware domain Knowledge Fusion and Fission method for continual test-time adaptation, called KFF, which adaptively expands and merges class-aware domain knowledge in old and new domains according to the test-time data from different domains, where discriminative historical knowledge can be dynamically accumulated. Specifically, considering the huge domain gap within streaming data, a domain Knowledge FIssion (KFI) module is designed to adaptively separate new domain knowledge from a paired class-aware domain prompt pool, alleviating the impact of negative knowledge brought by old domains that are distinct from the current domain. Besides, to avoid the cumulative computation and storage overheads from continuously fissioning new knowledge, a domain Knowledge FUsion (KFU) module is further designed to merge the fissioned new knowledge into the existing knowledge pool with minimal cost, where a greedy knowledge dynamic merging strategy is designed to improve the compatibility of new and old knowledge while keeping the computational efficiency. Extensive experiments on the ImageNet-C dataset verify the effectiveness of our proposed method against other methods.
- 7 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10932-10948
Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification
Lifelong person re-identification (LReID) suffers from the catastrophic forgetting problem when learning from non-stationary data streams. Existing exemplar-based and knowledge distillation-based LReID methods encounter data privacy and limited acquisition capacity, respectively. In this paper, we introduce the prototype, which is under-investigated in LReID, to better balance knowledge retention and acquisition. Previous prototype-based works primarily focused on the classification task, where prototypes were modeled as discrete points or statistical distributions. However, they either discarded the distribution information or omitted instance-level diversity, which are crucial fine-grained clues for LReID. Furthermore, the domain shifts between data sources result in a feature gap between the new and old data, which restricts the utilization of the fine-grained information in prototypes. To address these challenges, we propose Distribution-aware Knowledge Aligning and Prototyping (DKP++), a novel framework for modeling and leveraging prototypes in LReID. First, an Instance-level Distribution Modeling network is introduced to capture the local diversity of each instance. Next, a Distribution-oriented Prototype Generation algorithm transforms the instance-level diversity into identity-level distributions which are stored as prototypes. Then, a Prototype-based Knowledge Transfer module distills the knowledge within the prototypes to the new model. To mitigate the impact of domain shifts during knowledge transfer, we introduce a privacy-friendly Distribution Aligning module that transforms new input data to fit the historical distribution, which is incorporated with feature-level alignment constraints to enhance the coherence between new and old knowledge, effectively improving historical prototype utilization. Extensive experiments demonstrate that our method achieves a superior balance between plasticity and stability, outperforming state-of-the-art LReID methods by a large margin.
- 7 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10932-10948
Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification
Lifelong person re-identification (LReID) suffers from the catastrophic forgetting problem when learning from non-stationary data streams. Existing exemplar-based and knowledge distillation-based LReID methods encounter data privacy and limited acquisition capacity, respectively. In this paper, we introduce the prototype, which is under-investigated in LReID, to better balance knowledge retention and acquisition. Previous prototype-based works primarily focused on the classification task, where prototypes were modeled as discrete points or statistical distributions. However, they either discarded the distribution information or omitted instance-level diversity, which are crucial fine-grained clues for LReID. Furthermore, the domain shifts between data sources result in a feature gap between the new and old data, which restricts the utilization of the fine-grained information in prototypes. To address these challenges, we propose Distribution-aware Knowledge Aligning and Prototyping (DKP++), a novel framework for modeling and leveraging prototypes in LReID. First, an Instance-level Distribution Modeling network is introduced to capture the local diversity of each instance. Next, a Distribution-oriented Prototype Generation algorithm transforms the instance-level diversity into identity-level distributions which are stored as prototypes. Then, a Prototype-based Knowledge Transfer module distills the knowledge within the prototypes to the new model. To mitigate the impact of domain shifts during knowledge transfer, we introduce a privacy-friendly Distribution Aligning module that transforms new input data to fit the historical distribution, which is incorporated with feature-level alignment constraints to enhance the coherence between new and old knowledge, effectively improving historical prototype utilization. Extensive experiments demonstrate that our method achieves a superior balance between plasticity and stability, outperforming state-of-the-art LReID methods by a large margin.
- Open Access
UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis
Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in real scenarios due to casual object occlusions and unsatisfactory data collected by 3D sensors. To this end, existing methods focus on enhancing point cloud quality by developing dedicated denoising and completion models. However, due to the isolation between the point cloud enhancement and downstream tasks, these methods fail to work in various real-world domains. In addition, the conflicting objectives between denoising and completing tasks further limit the ensemble paradigm to preserve critical geometric features. To tackle the above challenges, we propose a unified point-level prompting method that reformulates point cloud denoising and completion as a prompting mechanism, enabling robust analysis in a parameter-efficient manner. We start by introducing a Rectification Prompter to adapt to noisy points through the predicted rectification vector prompts, effectively filtering noise while preserving intricate geometric features essential for accurate analysis. Sequentially, we further incorporate a Completion Prompter to generate auxiliary point prompts based on the rectified point clouds, facilitating their robustness and adaptability. Finally, a Shape-Aware Unit module is exploited to efficiently unify and capture the filtered geometric features for the downstream point cloud analysis.Extensive experiments on four datasets demonstrate the superiority and robustness of our method when handling noisy and incomplete point cloud data against existing state-of-the-art methods. Our code is released at https://github.com/zhoujiahuan1991/ICCV2025-UPP.
Open AccessUPP: Unified Point-Level Prompting for Robust Point Cloud Analysis
Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in real scenarios due to casual object occlusions and unsatisfactory data collected by 3D sensors. To this end, existing methods focus on enhancing point cloud quality by developing dedicated denoising and completion models. However, due to the isolation between the point cloud enhancement and downstream tasks, these methods fail to work in various real-world domains. In addition, the conflicting objectives between denoising and completing tasks further limit the ensemble paradigm to preserve critical geometric features. To tackle the above challenges, we propose a unified point-level prompting method that reformulates point cloud denoising and completion as a prompting mechanism, enabling robust analysis in a parameter-efficient manner. We start by introducing a Rectification Prompter to adapt to noisy points through the predicted rectification vector prompts, effectively filtering noise while preserving intricate geometric features essential for accurate analysis. Sequentially, we further incorporate a Completion Prompter to generate auxiliary point prompts based on the rectified point clouds, facilitating their robustness and adaptability. Finally, a Shape-Aware Unit module is exploited to efficiently unify and capture the filtered geometric features for the downstream point cloud analysis.Extensive experiments on four datasets demonstrate the superiority and robustness of our method when handling noisy and incomplete point cloud data against existing state-of-the-art methods. Our code is released at https://github.com/zhoujiahuan1991/ICCV2025-UPP.