# Generative Feature Replay For Class-Incremental Learning

arXiv: https://arxiv.org/abs/2004.09199 · HTML: https://mlsanity.com/paper/2004.09199/

## Key facts

- Cited by 109 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

## Built on by (most cited first, 30 of 109)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Training Networks in Null Space of Feature Covariance for Continual Learning](https://mlsanity.com/paper/2103.07113/) (2021)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Memory Replay with Data Compression for Continual Learning](https://mlsanity.com/paper/2202.06592/) (2022)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning](https://mlsanity.com/paper/2101.00407/) (2021)
- [Continual Learning with Foundation Models: An Empirical Study of Latent Replay](https://mlsanity.com/paper/2205.00329/) (2022)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [Model Zoo: A Growing "Brain" That Learns Continually](https://mlsanity.com/paper/2106.03027/) (2021)
- [Class-Incremental Learning with Generative Classifiers](https://mlsanity.com/paper/2104.10093/) (2021)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [Continually Learning Self-Supervised Representations with Projected Functional Regularization](https://mlsanity.com/paper/2112.15022/) (2021)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay](https://mlsanity.com/paper/2106.09835/) (2021)
- [Exemplar-free Continual Representation Learning via Learnable Drift Compensation](https://mlsanity.com/paper/2407.08536/) (2024)
- [Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer](https://mlsanity.com/paper/2101.09536/) (2021)
- [CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2505.24816/) (2025)
- [Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization](https://mlsanity.com/paper/2203.13167/) (2022)
- [Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning](https://mlsanity.com/paper/2409.01128/) (2024)
- [Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners](https://mlsanity.com/paper/2201.04924/) (2022)
- [It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher](https://mlsanity.com/paper/2203.17008/) (2022)
- [On the importance of cross-task features for class-incremental learning](https://mlsanity.com/paper/2106.11930/) (2021)
- [Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence](https://mlsanity.com/paper/2412.13779/) (2024)
- [GRASP: A Rehearsal Policy for Efficient Online Continual Learning](https://mlsanity.com/paper/2308.13646/) (2023)
- [ACAE-REMIND for Online Continual Learning with Compressed Feature Replay](https://mlsanity.com/paper/2105.08595/) (2021)
- [Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion](https://mlsanity.com/paper/2503.13769/) (2025)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Continual learning in cross-modal retrieval](https://mlsanity.com/paper/2104.06806/) (2021)

## Abstract (arXiv)

Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the task-ID is unknown at inference time. The imbalance between old and new classes typically results in a bias of the network towards the newest ones. This imbalance problem can either be addressed by storing exemplars from previous tasks, or by using image replay methods. However, the latter can only be applied to toy datasets since image generation for complex datasets is a hard problem. We propose a solution to the imbalance problem based on generative feature replay which does not require any exemplars. To do this, we split the network into two parts: a feature extractor and a classifier. To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor. Through feature generation, our method reduces the complexity of generative replay and prevents the imbalance problem. Our approach is computationally efficient and scalable to large datasets. Experiments confirm that our approach achieves state-of-the-art results on CIFAR-100 and ImageNet, while requiring only a fraction of the storage needed for exemplar-based continual learning. Code available at urlhttps://github.com/xialeiliu/GFR-IL.