Papers › CBA: Improving Online Continual Learning via Continual Bias Adaptor

CBA: Improving Online Continual Learning via Continual Bias Adaptor

14 Aug 2023ICCV 2023 1arXiv:2308.06925archive 2025-07-28

Quanziang Wang, Renzhen Wang, Yichen Wu, Xixi Jia, Deyu Meng

Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily forgets the previously learned knowledge and biases toward the newly received task. To address this problem, we propose a Continual Bias Adaptor (CBA) module to augment the classifier network to adapt to catastrophic distribution change during training, such that the classifier network is able to learn a stable consolidation of previously learned tasks. In the testing stage, CBA can be removed which introduces no additional computation cost and memory overhead. We theoretically reveal the reason why the proposed method can effectively alleviate catastrophic distribution shifts, and empirically demonstrate its effectiveness through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wqza/cba-online-cl officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continual Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections