Class-Incremental Learning using Diffusion Model for Distillation and Replay

2023-06-30 · Quentin Jodelet, Xin Liu, Yin Jun Phua, Tsuyoshi Murata

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate catastrophic forgetting. In this work, following the recent breakthrough in text-to-image generative models and their wide distribution, we propose the use of a pretrained Stable Diffusion model as a source of additional data for class-incremental learning. Compared to competitive methods that rely on external, often unlabeled, datasets of real images, our approach can generate synthetic samples belonging to the same classes as the previously encountered images. This allows us to use those additional data samples not only in the distillation loss but also for replay in the classification loss. Experiments on the competitive benchmarks CIFAR100, ImageNet-Subset, and ImageNet demonstrate how this new approach can be used to further improve the performance of state-of-the-art methods for class-incremental learning on large scale datasets.

📄 PDF Abstract BibTeX arXiv:2306.17560

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learning Class Incremental Learning Incremental Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

SER-Diff: Synthetic Error Replay Diffusion for Incremental Brain Tumor Segmentation

2025-10-06 · Sashank Makanaboyina arxiv

Incremental brain tumor segmentation is critical for models that must adapt to evolving clinical datasets without retraining on all prior data. However, catastrophic forgetting, where models lose previously acquired know…

Brain Tumor Segmentation Knowledge Distillation Incremental Learning

SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection

2024-02-27 · CVPR 2024 1 · Junsu Kim, Hoseong Cho, Jihyeon Kim, Yihalem Yimolal Tiruneh 외

In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. Howev…

class-incremental learning Class Incremental Learning Class-Incremental Object Detection Incremental Learning+3

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

2021-06-17 · ICCV 2021 10 · James Smith, Yen-Chang Hsu, Jonathan Balloch, Yilin Shen 외

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previous…

class-incremental learning Class Incremental Learning Incremental Learning

Continual Learning of Diffusion Models with Generative Distillation

2023-11-23 · Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M. van de Ven

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning wou…

Continual Learning Denoising Image Generation

Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay

2021-06-17 · Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

This paper proposes two novel knowledge transfer techniques for class-incremental learning (CIL). First, we propose data-free generative replay (DF-GR) to mitigate catastrophic forgetting in CIL by using synthetic sample…

class-incremental learning Class Incremental Learning Incremental Learning Knowledge Distillation+1