AI Paper Atlas

Research map / Continual learning / Online and replay-based

Dual-CBA: Improving Online Continual Learning via Dual Continual Bias Adaptors From a Bi-level Optimization Perspective

Hong Wang, Renzhen Wang, Yichen Wu, Xixi Jia, Minghao Zhou, Deyu Meng

TPAMI 2026 · Continual learning › Online and replay-based · approach: Plug-and-play online training enhancements · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add class-specific CBA to ER (ablation)ER · Split CIFAR-100 (M=2k)ACC (%): 21.66 -> 25.56Improved
upgrade class-specific CBA to Dual-CBA on ERER-CBA · Split CIFAR-100 (M=2k)ACC (%): 25.56 -> 29.14Improved
add Dual-CBA to ERER · Split CIFAR-10 (M=0.2k)FM (%): 49.81 -> 28.24Improved
add Dual-CBA to DER++DER++ · Split CIFAR-100 (M=5k)ACC (%): 17.36 -> 29.87Improved
add Dual-CBA to RARRAR · Split CIFAR-10 (M=0.5k)ACC (%): 47.66 -> 47.68No clear effect
add class-agnostic CBA to individual class-specific CBA (ablation)Dual-CBA · Split CIFAR-100 (M=5k)ACC (%): 31.63 -> 31.86Improved
use individual class-specific CBAs for old and new tasks instead of a single one (ablation)ER-Dual-CBA · Split CIFAR-100 (M=2k)ACC (%): 28.79 -> 29.31Improved
add class-specific CBA to class-agnostic CBA (ablation)ER-Dual-CBA-1 · Split CIFAR-100 (M=2k)ACC (%): 29.76 -> 29.81No clear effect
replace BN with Incremental BN (ablation)ER-Dual-CBA · Split CIFAR-100ACC (%): 25.29 -> 29.14Improved
replace BN with Incremental BN (ablation)ER · Split CIFAR-100FM (%): 33.21 -> 33.16No clear effect
replace BN with Incremental BN (ablation)DER++ · Split CIFAR-100FM (%): 41.35 -> 42.47Hurt
add class-specific CBA under semi-supervised label ratio 0.2ER · Split CIFAR-100 (M=2k)ACC (%): 16.38 -> 15.98Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy