mlsanityData to 7 Oct 2026

MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning

arXiv 2304.05362 ↗First posted 8 Apr 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Few Shot Class Incremental Learning (FSCIL) with few examples per class for each incremental session is the realistic setting of continual learning since obtaining large number of annotated samples is not feasible and cost effective. We present the framework MASIL as a step towards learning the maximal separable classifier. It addresses the common problem i.e forgetting of old classes and over-fitting to novel classes by learning the classifier weights to be maximally separable between classes forming a simplex Equiangular Tight Frame. We propose the idea of concept factorization explaining the collapsed features for base session classes in terms of concept basis and use these to induce classifier simplex for few shot classes. We further adds fine tuning to reduce any error occurred during factorization and train the classifier jointly on base and novel classes without retaining any base class samples in memory. Experimental results on miniImageNet, CIFAR-100 and CUB-200 demonstrate that MASIL outperforms all the benchmarks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 56 of its 86 references that are in the map. First posted on arXiv 8 Apr 2023.

Builds on

56 of 86 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2016Learning without Forgettingcited by 2,465
  10. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
38 more
  1. 2017Continual Learning with Deep Generative Replaycited by 1,152
  2. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  3. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  4. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  5. 2019Large Scale Incremental Learningcited by 727
  6. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 713
  7. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  8. 2018End-to-End Incremental Learningcited by 596
  9. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  10. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  11. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  12. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  13. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  14. 2018Learning without Memorizingcited by 249
  15. 2020Few-Shot Class-Incremental Learningcited by 249
  16. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  17. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  18. 2021Efficient and Modular Implicit Differentiationcited by 199
  19. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  20. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  21. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  22. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  23. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  24. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  25. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
  26. 2022Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learningcited by 118
  27. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
  28. 2019Continual Learning via Neural Pruningcited by 101
  29. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
  30. 2022Constrained Few-shot Class-incremental Learningcited by 93
  31. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  32. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
  33. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
  34. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
  35. 2020MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learningcited by 61
  36. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
  37. 2023Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Datacited by 40
  38. 2022Energy-based Latent Aligner for Incremental Learningcited by 37

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Few-shot Class-Incremental Learning via Generative Co-Memory Regularizationcited by 0
  2. 2026PKI: Prior Knowledge-Infused Neural Network for Few-Shot Class-Incremental Learningcited by 0