.png){kind=icon}
返回
Generative feature-driven image replay for continual learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.imavis.2024.105187.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the training on subsequent tasks. However, this is not always possible, e.g., due to data protection regulations. In such restricted scenarios, one can employ generative models to replay either artificial images or hidden features to a classifier. In this work, we propose Genifer (GENeratIve FEature-driven image Replay), where a generative model is trained to replay images that must induce the same hidden features as real samples when they are passed through the classifier. Our technique therefore incorporates the benefits of both image and feature replay, i.e.: (1) unlike conventional image replay, our generative model explicitly learns the distribution of features that are relevant for classification; (2) in contrast to feature replay, our entire classifier remains trainable; and (3) we can leverage image-space augmentations, which increase distillation performance while also mitigating overfitting during the training of the generative model. We show that Genifer substantially outperforms the previous state of the art for various settings on the CIFAR-100 and CUB-200 datasets. The code is available at:https://github.com/kevthan/feature-driven-image-replay.
Keyword:
Class-incremental learning
Generative replay
Catastrophic forgetting
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
Generative appearance replay for continual unsupervised domain adaptation.png)
MEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏A comprehensive study of class incremental learning algorithms for visual tasksNEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏分享收藏Brain-inspired replay for continual learning with artificial neural networksNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
查看更多内容