# GAN Memory with No Forgetting

arXiv: https://arxiv.org/abs/2006.07543 · HTML: https://mlsanity.com/paper/2006.07543/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2020.

## Built on by (most cited first, 30 of 84)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Distilling Causal Effect of Data in Class-Incremental Learning](https://mlsanity.com/paper/2103.01737/) (2021)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Synthesizing Informative Training Samples with GAN](https://mlsanity.com/paper/2204.07513/) (2022)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay](https://mlsanity.com/paper/2207.11213/) (2022)
- [Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference](https://mlsanity.com/paper/2110.10031/) (2021)
- [R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning](https://mlsanity.com/paper/2203.13104/) (2022)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Efficient Feature Transformations for Discriminative and Generative Continual Learning](https://mlsanity.com/paper/2103.13558/) (2021)
- [Natural continual learning: success is a journey, not (just) a destination](https://mlsanity.com/paper/2106.08085/) (2021)
- [SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection](https://mlsanity.com/paper/2402.17323/) (2024)
- [Class-Incremental Learning with Generative Classifiers](https://mlsanity.com/paper/2104.10093/) (2021)
- [CLAD: A realistic Continual Learning benchmark for Autonomous Driving](https://mlsanity.com/paper/2210.03482/) (2022)
- [Few-shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2210.16559/) (2022)
- [Fair Generative Models via Transfer Learning](https://mlsanity.com/paper/2212.00926/) (2022)
- [DiffClass: Diffusion-Based Class Incremental Learning](https://mlsanity.com/paper/2403.05016/) (2024)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)
- [Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners](https://mlsanity.com/paper/2201.04924/) (2022)
- [Do Pre-trained Models Benefit Equally in Continual Learning?](https://mlsanity.com/paper/2210.15701/) (2022)
- [Exploring Incompatible Knowledge Transfer in Few-shot Image Generation](https://mlsanity.com/paper/2304.07574/) (2023)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Efficient Conditional GAN Transfer with Knowledge Propagation across Classes](https://mlsanity.com/paper/2102.06696/) (2021)
- [Provable Contrastive Continual Learning](https://mlsanity.com/paper/2405.18756/) (2024)
- [CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks](https://mlsanity.com/paper/2103.04032/) (2021)
- [Continual Learning for Generative AI: From LLMs to MLLMs and Beyond](https://mlsanity.com/paper/2506.13045/) (2025)
- [Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2](https://mlsanity.com/paper/2208.05056/) (2022)

## Abstract (arXiv)

As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. Motivated by that, we propose a GAN memory for lifelong learning, which is capable of remembering a stream of datasets via generative processes, with no forgetting. Our GAN memory is based on recognizing that one can modulate the "style" of a GAN model to form perceptually-distant targeted generation. Accordingly, we propose to do sequential style modulations atop a well-behaved base GAN model, to form sequential targeted generative models, while simultaneously benefiting from the transferred base knowledge. The GAN memory -- that is motivated by lifelong learning -- is therefore itself manifested by a form of lifelong learning, via forward transfer and modulation of information from prior tasks. Experiments demonstrate the superiority of our method over existing approaches and its effectiveness in alleviating catastrophic forgetting for lifelong classification problems. Code is available at https://github.com/MiaoyunZhao/GANmemoryLifelongLearning.