# DiffClass: Diffusion-Based Class Incremental Learning

arXiv: https://arxiv.org/abs/2403.05016 · HTML: https://mlsanity.com/paper/2403.05016/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 56 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://mlsanity.com/paper/2204.04662/) (2022)
- [FearNet: Brain-Inspired Model for Incremental Learning](https://mlsanity.com/paper/1711.10563/) (2017)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (2022)
- [In-Context Learning Unlocked for Diffusion Models](https://mlsanity.com/paper/2305.01115/) (2023)
- [GAN Memory with No Forgetting](https://mlsanity.com/paper/2006.07543/) (2020)

## Built on by (most cited first, 23 of 23)

- [Synthetic Data is an Elegant GIFT for Continual Vision-Language Models](https://mlsanity.com/paper/2503.04229/) (2025)
- [F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning](https://mlsanity.com/paper/2403.15751/) (2024)
- [Does Training with Synthetic Data Truly Protect Privacy?](https://mlsanity.com/paper/2502.12976/) (2025)
- [Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.16064/) (2024)
- [On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning](https://mlsanity.com/paper/2501.15454/) (2025)
- [Towards Incremental Learning in Large Language Models: A Critical Review](https://mlsanity.com/paper/2404.18311/) (2024)
- [Future-Proofing Class-Incremental Learning](https://mlsanity.com/paper/2404.03200/) (2024)
- [Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection](https://mlsanity.com/paper/2603.19145/) (2026)
- [Harmony: A Unified Framework for Modality Incremental Learning](https://mlsanity.com/paper/2504.13218/) (2025)
- [Elastic Weight Consolidation Done Right for Continual Learning](https://mlsanity.com/paper/2603.18596/) (2026)
- [LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning](https://mlsanity.com/paper/2507.13568/) (2025)
- [Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2507.13739/) (2025)
- [Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge](https://mlsanity.com/paper/2503.23402/) (2025)
- [Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models](https://mlsanity.com/paper/2512.13072/) (2025)
- [LibContinual: A Comprehensive Library towards Realistic Continual Learning](https://mlsanity.com/paper/2512.22029/) (2025)
- [Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning](https://mlsanity.com/paper/2504.08982/) (2025)
- [Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture](https://mlsanity.com/paper/2504.15171/) (2025)
- [Exemplar-Free Continual Learning for State Space Models](https://mlsanity.com/paper/2505.18604/) (2025)
- [VidCLearn: A Continual Learning Approach for Text-to-Video Generation](https://mlsanity.com/paper/2509.16956/) (2025)
- [Deep Generative Continual Learning using Functional LoRA: FunLoRA](https://mlsanity.com/paper/2510.02631/) (2025)
- [Dream2Learn: Structured Generative Dreaming for Continual Learning](https://mlsanity.com/paper/2603.01935/) (2026)
- [Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth](https://mlsanity.com/paper/2604.00067/) (2026)
- [Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning](https://mlsanity.com/paper/2607.22994/) (2026)

## Abstract (arXiv)

Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exemplar-free CIL methods attempt to mitigate catastrophic forgetting by synthesizing previous task data. However, they fail to overcome the catastrophic forgetting due to the inability to deal with the significant domain gap between real and synthetic data. To overcome these issues, we propose a novel exemplar-free CIL method. Our method adopts multi-distribution matching (MDM) diffusion models to unify quality and bridge domain gaps among all domains of training data. Moreover, our approach integrates selective synthetic image augmentation (SSIA) to expand the distribution of the training data, thereby improving the model's plasticity and reinforcing the performance of our method's ultimate component, multi-domain adaptation (MDA). With the proposed integrations, our method then reformulates exemplar-free CIL into a multi-domain adaptation problem to implicitly address the domain gap problem to enhance model stability during incremental training. Extensive experiments on benchmark class incremental datasets and settings demonstrate that our method excels previous exemplar-free CIL methods and achieves state-of-the-art performance.