mlsanityData to 7 Oct 2026

CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning

arXiv 2601.08519 ↗First posted 13 Jan 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot class-incremental learning (FSCIL) receives significant attention from the public to perform classification continuously with a few training samples, which suffers from the key catastrophic forgetting problem. Existing methods usually employ an external memory to store previous knowledge and treat it with incremental classes equally, which cannot properly preserve previous essential knowledge. To solve this problem and inspired by recent distillation works on knowledge transfer, we propose a framework termed Constrained Dataset Distillation (CD2) to facilitate FSCIL, which includes a dataset distillation module (DDM) and a distillation constraint module~(DCM). Specifically, the DDM synthesizes highly condensed samples guided by the classifier, forcing the model to learn compacted essential class-related clues from a few incremental samples. The DCM introduces a designed loss to constrain the previously learned class distribution, which can preserve distilled knowledge more sufficiently. Extensive experiments on three public datasets show the superiority of our method against other state-of-the-art competitors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  8. 2019Relational Knowledge Distillationcited by 873
  9. 2018End-to-End Incremental Learningcited by 596
  10. 2020Dataset Condensation with Gradient Matchingcited by 510
  11. 2022Dataset Distillation by Matching Training Trajectoriescited by 437
  12. 2020Few-Shot Class-Incremental Learningcited by 249
23 more
  1. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 187
  2. 2022Dataset Distillation using Neural Feature Regressioncited by 177
  3. 2022Minimizing the Accumulated Trajectory Error to Improve Dataset Distillationcited by 142
  4. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  5. 2023Improved Distribution Matching for Dataset Condensationcited by 124
  6. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
  7. 2022Efficient Dataset Distillation Using Random Feature Approximationcited by 111
  8. 2022Dataset Condensation with Contrastive Signalscited by 105
  9. 2019Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Datacited by 103
  10. 2022Constrained Few-shot Class-incremental Learningcited by 93
  11. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
  12. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
  13. 2023M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancycited by 49
  14. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  15. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  16. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  17. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  18. 2022Meta Knowledge Condensation for Federated Learningcited by 26
  19. 2024OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learningcited by 25
  20. 2023EAT: Towards Long-Tailed Out-of-Distribution Detectioncited by 16
  21. 2024What is Dataset Distillation Learning?cited by 13
  22. 2024Rethinking Few-shot Class-incremental Learning: Learning from Yourselfcited by 13
  23. 2022Learnable Distribution Calibration for Few-Shot Class-Incremental Learningcited by 12

Built on by

Not cited yet.