Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries

Jihwan Bang, Hyunseo Koh, Seulki Park, Hwanjun Song, Jung-Woo Ha, Jonghyun Choi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 9275-9284

Abstract


Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. Large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored. We consider a more practical CL setup of an online learning from blurry data stream with corrupted noise, where existing CL methods struggle. To address the task, we first argue the importance of both diversity and purity of examples in the episodic memory of continual learning models. To balance diversity and purity in the episodic memory, we propose a novel strategy to manage and use the memory by a unified approach of label noise aware diverse sampling and robust learning with semi-supervised learning. Our empirical validations on four real-world or synthetic benchmark datasets (CIFAR10 and 100, mini-WebVision, and Food-101N) show that our method significantly outperforms prior arts in this realistic and challenging continual learning scenario.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bang_2022_CVPR, author = {Bang, Jihwan and Koh, Hyunseo and Park, Seulki and Song, Hwanjun and Ha, Jung-Woo and Choi, Jonghyun}, title = {Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {9275-9284} }