Proceedings

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

Kexin Bao, Daichi Zhang, Hansong Zhang, Yong Li, Yutao Yue, Shiming Ge

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 4761-4769.

https://doi.org/10.24963/ijcai.2025/530

Keywords

  • Machine Learning: ML: Incremental learning
  • Machine Learning: ML: Few-shot learning
  • Computer Vision: CV: Recognition (object detection, categorization)
  • Computer Vision: CV: Image and video synthesis and generation

Abstract

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 (CD^2) 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.

Kexin Bao, Daichi Zhang, Hansong Zhang, Yong Li, Yutao Yue, and Shiming Ge. 2025. CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 4761–4769. https://doi.org/10.24963/ijcai.2025/530
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards