mlsanityData to 7 Oct 2026

Continual Learning by Three-Phase Consolidation

arXiv 2403.14679 ↗First posted 12 Mar 2024cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgetting of previous knowledge. Each experience (a.k.a. task) is learned in three phases characterized by different rules and learning dynamics, aimed at removing the class-bias problem (due to class unbalancing) and limiting gradient-based corrections to prevent forgetting of underrepresented classes. Several experiments on complex datasets demonstrate its accuracy and efficiency advantages over competitive existing approaches. The algorithm and all the results presented in this paper are fully reproducible thanks to its publication on the Avalanche open framework for continual learning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 12 Mar 2024.

Builds on

31 of 48 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  9. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  10. 2019Large Scale Incremental Learningcited by 727
  11. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  12. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
19 more
  1. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  2. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 281
  3. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  4. 2018Selective Experience Replay for Lifelong Learningcited by 239
  5. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 215
  6. 2019Continual Unsupervised Representation Learningcited by 147
  7. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  8. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  9. 2019Latent Replay for Real-Time Continual Learningcited by 97
  10. 2021Representational Continuity for Unsupervised Continual Learningcited by 95
  11. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  12. 2019Rehearsal-Free Continual Learning over Small Non-I.I.D. Batchescited by 46
  13. 2019Semantic-Aware Scene Recognitioncited by 43
  14. 2023Avalanche: A PyTorch Library for Deep Continual Learningcited by 33
  15. 2019Unsupervised Progressive Learning and the STAM Architecturecited by 29
  16. 2021Continual Learning in Deep Networks: an Analysis of the Last Layercited by 17
  17. 2023Class-Incremental Learning with Repetitioncited by 9
  18. 2022Generative Negative Replay for Continual Learningcited by 4
  19. 2023Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learningcited by 1

Built on by

Not cited yet.