Related work

The foundational work on continual learning, 1988 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

10 papers of 6,984Sort Recent · Most cited
  1. 2024
    SDCoT++: Improved Static-Dynamic Co-Teaching for Class-Incremental 3D Object DetectionNa Zhao, Peisheng Qian, Fang Wu … Gim Hee LeeTIP · Singapore University of Technology and Design · National University of Singapore · +2
  2. 2024PDF ↗
  3. 2024
    Relationship-Incremental Scene Graph Generation by a Divide-and-Conquer Pipeline With Feature AdapterXuewei Li, Guangcong Zheng, Yunlong Yu … Xi LiTIP · Zhejiang University of Science and Technology · Zhejiang University · +1
  4. 2024
  5. 2024
    Class-Incremental Unsupervised Domain Adaptation via Pseudo-Label DistillationKun Wei, Xu Yang, Zhe Xu, Cheng DengTIP · Xidian University
  6. 2024
    Layer-Specific Knowledge Distillation for Class Incremental Semantic SegmentationQilong Wang, Yiwen Wu, Yang Liu … Qinghua HuTIP · Tianjin University · Harbin Institute of Technology · +1
  7. 2024
    NTK-Guided Few-Shot Class Incremental LearningJingren Liu, Zhong Ji, Yanwei Pang, Yunlong YuTIP · Tianjin University · Zhejiang University
    PDF ↗
  8. 2024
    Model Attention Expansion for Few-Shot Class-Incremental LearningXuan Wang, Zhong Ji, Yunlong Yu … Jungong HanTIP · Tianjin University · Zhejiang University · +1
  9. 2024
    Balanced Destruction-Reconstruction Dynamics for Memory-Replay Class Incremental LearningYuhang Zhou, Jiangchao Yao, Feng Hong … Yanfeng WangTIP · Shanghai Artificial Intelligence Laboratory
    PDF ↗
  10. 2024
    PAMK: Prototype Augmented Multi-Teacher Knowledge Transfer Network for Continual Zero-Shot LearningJunxin Lu, Shiliang SunTIP · East China Normal University · Shanghai Jiao Tong University
About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. It lists only papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or led by someone who has published there, or cited a few hundred times. Preprints that later get accepted, and authors who later publish at those venues, are picked up by the weekly run. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.