avatar

Da-Wei Zhou

avatar
Associate Researcher
School of Artificial Intelligence, Nanjing University
zhoudw (at) lamda.nju.edu.cn

Short Bio

I am an Associate Researcher (2024-) in the School of Artificial Intelligence at Nanjing University. I am a member of LAMDA Group. Previously, I received my Ph.D. (2018-2024) from Nanjing University, advised by Prof. De-Chuan Zhan and Prof. Han-Jia Ye. I was fortunate to visit MMLab@NTU (2022-2023), working closely with Prof. Ziwei Liu.

My research interests include machine learning and its applications in computer vision, currently focusing on continual learning, pre-trained model reuse, and multimodal large language models.

  I am looking for highly self-motivated students. Please drop me an email with your resume and transcript if you are interested in working together with me.

News

  • [2025-05] Two papers are accepted to ICML 2025.
  • [2025-04] One survey about model reuse is accepted to IJCAI 2025.
  • [2025-03] One paper about class-incremental learning with CLIP is uploaded to arXiv.
  • [2025-02] Two papers about continual learning are accepted to CVPR 2025.
  • [2025-02] One paper about class-incremental learning with VLM is accepted to TPAMI.
  • [2025-01] Our toolbox for class-incremental learning with PTMs (PILOT) is accepted to SCIS.
  • [2024-12] One paper about class-incremental learning is accepted to AAAI 2025.
  • [2024-11] Recognized as NeurIPS 2024 Top Reviewer.
  • [2024-10] We are hosting a tutorial on model reuse at AAAI 2025.
  • [2024-09] One paper about class-incremental learning with PTM is accepted to MLJ.
  • [2024-08] One paper about class-incremental learning with PTM is accepted to IJCV.
  • [2024-07] One survey about class-incremental learning is accepted to TPAMI.
  • [2024-05] Successfully defended my Ph.D. dissertation.
  • [2024-05] Recognized as CVPR 2024 Outstanding Reviewer.
  • [2024-05] One paper about class-incremental learning is accepted to ICML 2024.
  • [2024-04] One survey about PTM-based continual learning is accepted to IJCAI 2024.
  • [2024-02] One paper about class-incremental learning is accepted to CVPR 2024.
  • [2023-11] Recognized as NeurIPS 2023 Top Reviewer.
  • [2023-09] One paper about few-shot class-incremental learning is accepted to NeurIPS 2023.
  • [2023-09] One paper about contextualized meta-learning is accepted to TPAMI.
  • [2023-08] We are hosting the tutorial (slides) on continual learning at IJCAI 2023.
  • [2023-01] Two papers about class-incremental learning are accepted to ICLR 2023 (one spotlight).
  • [2022-10] Our toolbox for class-incremental learning (PyCIL) is accepted to SCIS.
  • [2022-08] One paper about few-shot class-incremental learning is accepted to TPAMI.
  • [2022-07] One paper about class-incremental learning is accepted to ECCV 2022.
  • [2022-03] One paper about few-shot class-incremental learning is accepted to CVPR 2022.
  • [2021-07] One paper about class-incremental learning is accepted to ACM MM 2021.
  • [2021-03] One oral paper about open-set recognition is accepted to CVPR 2021.

    • Selected Publications

    For more details, please view the full publication page or Google Scholar profile.

    Preprints

    1. Preprint
      External Knowledge Injection for CLIP-Based Class-Incremental Learning
      Da-Wei Zhou, Kai-Wen Li, Jingyi Ning, Han-Jia Ye, Lijun Zhang, De-Chuan Zhan
      arXiv 2025
      [Paper] [Code]

    Conference Paper

    1. CVPR
      Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning
      Da-Wei Zhou, Zi-Wen Cai, Han-Jia Ye, Lijun Zhang, De-Chuan Zhan
      The IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2025
      [Paper] [Code] [Media]
    2. CVPR
      Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
      Bowen Zheng, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
      The IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2025
      [Paper] [Code]
    3. ICML
      Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
      Lan Li, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
      International Conference on Machine Learning. ICML 2025
      [Paper] [Code]
    4. ICML
      Parrot: Multilingual Visual Instruction Tuning
      Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye
      International Conference on Machine Learning. ICML 2025
      [Paper] [Code]
    5. IJCAI
      A Unifying Perspective on Model Reuse: From Small to Large Pre-Trained Models
      Da-Wei Zhou, Han-Jia Ye
      International Joint Conference on Artificial Intelligence. IJCAI 2025
      [Paper] [Project Page]
    6. CVPR
      Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
      Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan
      The IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2024
      [Paper] [Code]
    7. IJCAI
      Continual Learning with Pre-Trained Models: A Survey
      Da-Wei Zhou, Hai-Long Sun, Jingyi Ning, Han-Jia Ye, De-Chuan Zhan
      International Joint Conference on Artificial Intelligence. IJCAI 2024
      Top-4 Most Influential IJCAI Papers
      [Paper] [Code] [Media]
    8. ICML
      Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
      Bowen Zheng, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
      International Conference on Machine Learning. ICML 2024
      [Paper] [Code]
    9. ICLR Spotlight
      A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
      Da-Wei Zhou, Qi-Wei Wang, Han-Jia Ye, De-Chuan Zhan
      International Conference on Learning Representations. ICLR 2023 Spotlight Presentation
      [Paper] [Code]
    10. ICLR
      BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion
      Fu-Yun Wang, Da-Wei Zhou, Liu Liu, Yatao Bian, Han-Jia Ye, De-Chuan Zhan, Peilin Zhao
      International Conference on Learning Representations. ICLR 2023
      [Paper] [Code]
    11. NeurIPS
      Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
      Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang, De-Chuan Zhan, Han-Jia Ye
      Neural Information Processing Systems. NeurIPS 2023
      [Paper] [Code]
    12. CVPR
      Forward Compatible Few-Shot Class-Incremental Learning
      Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma, Shiliang Pu, De-Chuan Zhan
      IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2022
      [Paper] [Code] [Project Page]
    13. ECCV
      FOSTER: Feature Boosting and Compression for Class-Incremental Learning
      Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
      European Conference on Computer Vision. ECCV 2022
      [Paper] [Code]
    14. CVPR Oral
      Learning Placeholders for Open-Set Recognition
      Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
      IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2021
      Oral Presentation
      [Paper] [Code] [Project Page]
    15. ACM MM
      Co-Transport for Class-Incremental Learning
      Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
      ACM International Conference on Multimedia. ACM MM 2021
      [Paper] [Code] [Project Page]

    Journal Article

    1. TPAMI
      Learning without Forgetting for Vision-Language Models
      Da-Wei Zhou, Yuanhan Zhang, Yan Wang, Jingyi Ning, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu
      IEEE Transactions on Pattern Analysis and Machine Intelligence. TPAMI 2025
      [Paper] [Code] [Media]
    2. TPAMI
      Class-Incremental Learning: A Survey
      Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu
      IEEE Transactions on Pattern Analysis and Machine Intelligence. TPAMI 2024
      TPAMI Popular Documents
      [Paper] [Code] [Media]
    3. TPAMI
      Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
      Da-Wei Zhou, Han-Jia Ye, Liang Ma, Di Xie, Shiliang Pu, De-Chuan Zhan
      IEEE Transactions on Pattern Analysis and Machine Intelligence. TPAMI 2023
      ESI Highly Cited Paper
      [Paper] [Code]
    4. IJCV
      Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
      Da-Wei Zhou, Zi-Wen Cai, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu
      International Journal of Computer Vision. IJCV 2025
      [Paper] [Code] [Media]
    5. TPAMI
      Contextualizing Meta-Learning via Learning to Decompose
      Han-Jia Ye, Da-Wei Zhou, Lanqing Hong, Zhenguo Li, Xiu-Shen Wei, De-Chuan Zhan
      IEEE Transactions on Pattern Analysis and Machine Intelligence. TPAMI 2024
      [Paper] [Code]
    6. SCIS
      PyCIL: A Python Toolbox for Class-Incremental Learning
      Da-Wei Zhou*, Fu-Yun Wang*, Han-Jia Ye, De-Chuan Zhan
      SCIENCE CHINA Information Sciences. SCIS 2023
      [Paper] [Code] [Media] [中文解读]

    Contact


    Many thanks to Yaoyao for sharing this great theme.