mlsanityData to 7 Oct 2026

TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning

arXiv 2312.04225 ↗First posted 7 Dec 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. TLCE minimizes interference between old and new classes by mapping old class images to quasi-orthogonal prototypes using episodic training. It then ensembles diverse pre-trained models to better adapt to novel classes despite data imbalance. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

37 of 47 references.

References · 37

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  9. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2018End-to-End Incremental Learningcited by 596
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
25 more
  1. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  2. 2020Few-Shot Class-Incremental Learningcited by 249
  3. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  4. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  5. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  6. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  7. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  8. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  9. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  10. 2022FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learningcited by 120
  11. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
  12. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  13. 2020Memory-Efficient Incremental Learning Through Feature Adaptationcited by 107
  14. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
  15. 2022Constrained Few-shot Class-incremental Learningcited by 93
  16. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
  17. 2022R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learningcited by 59
  18. 2021Few-Shot Lifelong Learningcited by 58
  19. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  20. 2020Continual Learning with Extended Kronecker-factored Approximate Curvaturecited by 39
  21. 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
  22. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  23. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  24. 2021Continual Learning in Deep Networks: an Analysis of the Last Layercited by 17
  25. 2023P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classificationcited by 1

Built on by

Not cited yet.