Continual Unsupervised Learning

Continual Unsupervised Learning is a machine learning paradigm that enables a model to incrementally acquire and retain knowledge from a continuous stream of unlabeled data while mitigating catastrophic forgetting, thereby distinguishing it from both traditional unsupervised learning and disjoint batch-based unsupervised learning approaches.

27

Publications

936

Citations

117

Authors

49

Institutions

Publications per year

2017–2026

25

Authors

117

  1. AM
    Abu Md Niamul Taufique

    Rochester Institute of Technology, United States

    3 publications · 48 citations

    3

    h-index

  2. AS
    Andreas Savakis

    Rochester Institute of Technology, United States

    3 publications · 48 citations

    3

    h-index

  3. CS
    Chowdhury Sadman Jahan

    Rochester Institute of Technology, United States

    3 publications · 48 citations

    3

    h-index

  4. TT
    Tinne Tuytelaars

    KU Leuven, Belgium

    2 publications · 58 citations

    2

    h-index

  5. DB
    D. Barrientos

    University of Liverpool, United Kingdom

    1 publications · 21 citations

    1

    h-index

1–5 of 117

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 129 citations

    3

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 44 citations

    2

    h-index

  3. 2

    h-index

  4. Frontiers in Neuroscience

    1 publications · 26 citations

    1

    h-index

  5. Medical Image Analysis

    1 publications · 17 citations

    1

    h-index

1–5