Sanqing Qu (瞿三清)

Hi there, welcome to my homepage! I am currently a postdoctoral researcher at Tongji University, where I am jointly supervised by Prof. Guang Chen and Prof. Changjun Jiang. I earned my Ph.D. from Tongji University in 2024.

My research focuses on transfer learning and its applications in Embodied AI and AI4Science.

Email  /  Google Scholar  /  Github

profile photo
News
  • 2025.03 : Our work (RCP-Bench), a benchmark developed to evaluate the robustness of collaborative perception is accepted by CVPR-2025. Kudos to Shihang!
  • 2025.01 : Our work (BMD-v2), a substantial extension to BMD is accepted by IJCV-2025.
  • 2024.12 : We win the first prize (1/226) in the 2nd Global AI Drug Development Algorithm Competition.
  • 2024.07 : Our work (HGL) on test-time domain adaptation for segmentation is accepted by ECCV-2024, Oral.
  • 2024.03 : Our work (GLC++), a substantial extension to GLC, is released.
  • 2024.02 : Our work (LEAD) on source-free universal domain adaptation is accepted by CVPR-2024.
  • Career and Education History
  • 2024.12 ~ Present : Postdoc, Tongji University.
  • 2020.09 ~ 2024.11 : Ph.D. student, Tongji University.
  • 2015.09 ~ 2020.07: Undergrad student, Tongji University.
  • Selected Publications

    * indicates equal contribution

    dise RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions
    Shihang Du, Sanqing Qu, Tianhang Wang, Xudong Zhang, Yunwei Zhu, Jian Mao, Fan Lu, Qiao Lin, Guang Chen
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
    [PDF] [Code]

    We introduce RCP-Bench, the first comprehensive benchmark designed to evaluate the robustness of collaborative detection models under a wide range of real-world corruptions. RCPBench includes three new datasets (i.e., OPV2V-C, V2XSet-C, and DAIR-V2X-C) that simulate six collaborative cases and 14 types of camera corruption resulting from external environmental factors, sensor failures, and temporal misalignments. Extensive experiments on 10 leading collaborative perception models reveal that, while these models perform well under ideal conditions, they are significantly affected by corruptions.

    dise General Class-Balanced Multicentric Dynamic Prototype Pseudo-Labeling for Source-Free Domain Adaptation
    Sanqing Qu, Guang Chen, Jing Zhang, Zhijun Li , Wei He , Dacheng Tao
    International Journal of Computer Vision (IJCV), 2025
    European Conference on Computer Vision (ECCV), 2022
    [PDF] [Code]

    We promote the vanilla BMD to BMD-v2 by incorporating a consistency-guided reweighting strategy to improve inter-class balanced sampling, and leveraging the silhouettes metric to realize adaptive intra-class multicentric clustering. Extensive experiments conducted on both 2D images and 3D point cloud recognition demonstrate that our proposed BMD strategy significantly improves existing representative methods.

    dise GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
    Sanqing Qu, Tianpei Zou, Florian Röhrbein, Cewu Lu, Guang Chen, Dacheng Tao , Changjun Jiang
    Arxiv Pre-print, 2024
    [arXiv] [Code]

    Despite the simple global and local clustering (GLC) technique achieving commendable performance in separating "known" and "unknown" data, its reliance on pseudo-labeling supervision, especially using uniform encoding for all "unknown" data limits its capacity to discriminate among different "unknown" categories. To alleviate this, we promote GLC to GLC++ by developing a new contrastive affinity learning strategy, sidestepping the need for a specialized source model structure.

    dise HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation
    Tianpei Zou*, Sanqing Qu*, Zhijun Li , Alois Knoll, Lianghua He, Guang Chen, Changjun Jiang
    European Conference on Computer Vision (ECCV), 2024
    [Arxiv] [Code]

    In this paper, we delve into TTA in 3D point cloud segmentation and propose a novel Hierarchical Geometry Learning (HGL) framework. HGL comprises three complementary modules from local, global to temporal learning in a bottom-up manner. Technically, we first construct a local geometry learning module for pseudo-label generation. Next, we build prototypes from the global geometry perspective for pseudo-label fine-tuning. Furthermore, we introduce a temporal consistency regularization module to mitigate negative transfer.

    dise LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
    Sanqing Qu, Tianpei Zou, Lianghua He, Florian Röhrbein, Alois Knoll, Guang Chen, Changjun Jiang
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024
    [arXiv] [Code]

    For Universal Domain Adaptation (UniDA), in this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data. This solution leads to elegant views for identifying target-private unknown data without tedious tuning thresholds or relying on iterative clustering.

    dise MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection
    Boyang Peng*, Sanqing Qu*, Yong Wu, Tianpei Zou, Lianghua He, Alois Knoll, Guang Chen, Changjun Jiang
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024
    [arXiv] [Code]

    In this paper, we target a practical setting in IP protection, i.e., Source-free Model IP protection. To achieve this, we propose a novel MAsk Pruning (MAP) framework. MAP stems from an intuitive hypothesis, i.e., there are target-related parameters in a well-trained model, locating and pruning them is the key to IP protection.

    dise Upcycling Models under Domain and Category Shift
    Sanqing Qu*, Tianpei Zou*, Florian Röhrbein, Cewu Lu, Guang Chen, Dacheng Tao , Changjun Jiang
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
    [arXiv] [PDF] [Code] [Slides] [Poster] [Video]

    In this paper, we explore the Source-free Universal Domain Adaptation (SF-UniDA). SF-UniDA is appealing in view that universal model adaptation can be resolved only on the basis of a standard pre-trained closed-set model, i.e., without source raw data and dedicated model architecture.

    dise Modality-Agnostic Debiasing for Single Domain Generalization
    Sanqing Qu, Yingwei Pan, Guang Chen, Ting Yao, Changjun Jiang, Tao Mei
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
    [arXiv] [PDF] [Slides] [Poster] [Video]

    Existing single-DG techniques commonly devise various data-augmentation algorithms, and remould the multi-source domain generalization methodology to learn domain-generalized (semantic) features. In contrast, we target a versatile Modality-Agnostic Debiasing (MAD) framework for single-DG, that enables generalization for different modalities.

    dise Neuromorphic Vision-based Fall Localization in Event Streams with Temporal–spatial Attention Weighted Network
    Guang Chen*, Sanqing Qu*, Zhijun Li , Haitao Zhu, Jiaxuan Dong, Min Liu, Jorg Conradt.
    IEEE Transactions on Cybernetics. (T-Cyber), 2022
    [IEEE]  

    In this paper, we proposed a bio-inspired event-camera based falls temporal localization framework. Specifically, we propose a event density-based action proposal generation scheme, and introduce a temporal-spatial attention mechanism for action modeling.

    dise ACM-Net: Action Context Modeling Network for Weakly-supervised Temporal Action Localization
    Sanqing Qu, Guang Chen, Zhijun Li , Lijun Zhang, Fan Lu , Alois Knoll.
    Arxiv Pre-print, 2021
    [arXiv] [Code]

    In this paper, we propose an action-context modeling network termed ACM-Net, which integrates a three-branch attention module to measure the likelihood of each temporal point being action instance, context, or non-action background, simultaneously.

    Honors and Awards

  • 2024 : The First Prize in the 2nd Global AI Drug Development Algorithm Competition (1/226).
  • 2022, 2021 : The Outstanding Doctoral Student Scholarship of Tongji University
  • 2020 : The Shanghai Outstanding Graduate
  • 2020 : The Second Prize of National Graduate Student Mathematical Modeling Contest
  • 2019 : The BaoGang Scholarship (宝钢教育奖)
  • 2018 : Rank 4th in 2018 Corolo-Cup of Germany Graduate Students
  • Academic Services

  • Journal Reviewer: IEEE TPAMI, IJCV, IEEE TIP, IEEE TMM, IEEE TCSVT, ACM TOMM, etc.
  • Conference Reviewer: CVPR, ICCV, ECCV, ICRA, IROS, etc.

  • Website Template


    © Sanqing Qu | Last updated: Mar 01, 2025