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

arXiv: https://arxiv.org/abs/2601.08519 · HTML: https://mlsanity.com/paper/2601.08519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Dataset Condensation via Efficient Synthetic-Data Parameterization](https://mlsanity.com/paper/2205.14959/) (2022)
- [Dataset Distillation using Neural Feature Regression](https://mlsanity.com/paper/2206.00719/) (2022)
- [Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation](https://mlsanity.com/paper/2211.11004/) (2022)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Improved Distribution Matching for Dataset Condensation](https://mlsanity.com/paper/2307.09742/) (2023)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Efficient Dataset Distillation Using Random Feature Approximation](https://mlsanity.com/paper/2210.12067/) (2022)
- [Dataset Condensation with Contrastive Signals](https://mlsanity.com/paper/2202.02916/) (2022)
- [Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data](https://mlsanity.com/paper/1912.07768/) (2019)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Few-Shot Class-Incremental Learning from an Open-Set Perspective](https://mlsanity.com/paper/2208.00147/) (2022)
- [Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay](https://mlsanity.com/paper/2207.11213/) (2022)
- [M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy](https://mlsanity.com/paper/2312.15927/) (2023)
- [A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks](https://mlsanity.com/paper/2311.07784/) (2023)
- [On the Soft-Subnetwork for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2209.07529/) (2022)
- [Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting](https://mlsanity.com/paper/2108.08165/) (2021)
- [Memorizing Complementation Network for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2208.05610/) (2022)
- [Meta Knowledge Condensation for Federated Learning](https://mlsanity.com/paper/2209.14851/) (2022)

## 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.