# Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay

arXiv: https://arxiv.org/abs/2207.11213 · HTML: https://mlsanity.com/paper/2207.11213/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for continual learning, one of 12 directions in Knowledge distillation.
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Placed in

- Knowledge distillation / [Distillation for continual learning](https://mlsanity.com/distill/distillation-for-continual-learning/)

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)
- [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Zero-shot Knowledge Transfer via Adversarial Belief Matching](https://mlsanity.com/paper/1905.09768/) (2019)
- [Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2107.08918/) (2021)
- [GAN Memory with No Forgetting](https://mlsanity.com/paper/2006.07543/) (2020)
- [Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity](https://mlsanity.com/paper/2112.05883/) (2021)
- [Memory-Free Generative Replay For Class-Incremental Learning](https://mlsanity.com/paper/2109.00328/) (2021)

## Built on by (most cited first, 30 of 72)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.00426/) (2023)
- [Consistent Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2403.08568/) (2024)
- [Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts](https://mlsanity.com/paper/2210.03885/) (2022)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [MetaGCD: Learning to Continually Learn in Generalized Category Discovery](https://mlsanity.com/paper/2308.11063/) (2023)
- [On the Soft-Subnetwork for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2209.07529/) (2022)
- [Few-shot Class-incremental Learning for Classification and Object Detection: A Survey](https://mlsanity.com/paper/2308.06764/) (2023)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues](https://mlsanity.com/paper/2309.09526/) (2023)
- [Adapting to Distribution Shift by Visual Domain Prompt Generation](https://mlsanity.com/paper/2405.02797/) (2024)
- [Generative Multi-modal Models are Good Class-Incremental Learners](https://mlsanity.com/paper/2403.18383/) (2024)
- [Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models](https://mlsanity.com/paper/2403.09296/) (2024)
- [Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2301.09964/) (2023)
- [Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants](https://mlsanity.com/paper/2308.01746/) (2023)
- [Rethinking Few-shot Class-incremental Learning: Learning from Yourself](https://mlsanity.com/paper/2407.07468/) (2024)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [How to Train the Teacher Model for Effective Knowledge Distillation](https://mlsanity.com/paper/2407.18041/) (2024)
- [Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2401.01598/) (2024)
- [Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2508.20265/) (2025)
- [CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2410.05627/) (2024)
- [Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning](https://mlsanity.com/paper/2403.04140/) (2024)
- [Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2407.06136/) (2024)
- [Semantic-visual Guided Transformer for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2303.15494/) (2023)
- [Continual Learning: Forget-free Winning Subnetworks for Video Representations](https://mlsanity.com/paper/2312.11973/) (2023)
- [Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2405.04918/) (2024)
- [Vision-Language Navigation with Continual Learning](https://mlsanity.com/paper/2409.02561/) (2024)

## Abstract (arXiv)

Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. Recently, a pioneer claims that the commonly used replay-based method in class-incremental learning (CIL) is ineffective and thus not preferred for FSCIL. This has, if truth, a significant influence on the fields of FSCIL. In this paper, we show through empirical results that adopting the data replay is surprisingly favorable. However, storing and replaying old data can lead to a privacy concern. To address this issue, we alternatively propose using data-free replay that can synthesize data by a generator without accessing real data. In observing the the effectiveness of uncertain data for knowledge distillation, we impose entropy regularization in the generator training to encourage more uncertain examples. Moreover, we propose to relabel the generated data with one-hot-like labels. This modification allows the network to learn by solely minimizing the cross-entropy loss, which mitigates the problem of balancing different objectives in the conventional knowledge distillation approach. Finally, we show extensive experimental results and analysis on CIFAR-100, miniImageNet and CUB-200 to demonstrate the effectiveness of our proposed one.