SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.15355 · CVPR · 2022

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

Jung-Woo Ha, Naver Lab, Hwanjun Song, Gist, Jihwan Bang, Jonghyun Choi, Seulki Park, Hyunseo Koh

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A 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 task setup of an online learning from blurry data stream with corrupted labels, 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 noise datasets (CI-FAR10 and 100, mini-WebVision, and Food-101N) exhibit that our method significantly outperforms prior arts in this realistic and challenging continual learning scenario. Code and data splits are available in https://github.com/ clovaai/puridiver.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.15355")
get_code_for_paper("2203.15355")
have("2203.15355")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.15355.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.15355.svg)](https://syntology.ai/paper/2203.15355)

Connect an agent — have() is free.