AI Paper Atlas

Research map / Continual learning / Class-incremental

Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning

Hongye Xu, Bartosz Krawczyk

ICLR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 1 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
replace AdaGauss two-stage drift compensation with BiCyc bidirectional cycle-consistent alignmentAdaGauss · CIFAR-100 T=10 (from scratch)A_last: 46.8 -> 50.6Improved
replace AdaGauss with BiCycAdaGauss · CIFAR-100 T=20 (from scratch)A_inc: 54.4 -> 56.5Improved
replace AdaGauss with BiCycAdaGauss · TinyImageNet T=20 (from scratch)A_inc: 39.5 -> 44.2Improved
replace AdaGauss with BiCycAdaGauss · TinyImageNet T=10 (from scratch)A_inc: 45.8 -> 49.1Improved
replace DPCR with BiCycDPCR · CIFAR-100 T=10 (from scratch)A_inc: 62.8 -> 63.2Improved
replace DPCR with BiCycDPCR · ImageNet-100 T=20 (from scratch)A_inc: 54.7 -> 58.2Improved
replace AdaGauss with BiCycAdaGauss · ImageNet-100 T=10 (from scratch)A_inc: 65.0 -> 66.8Improved
replace AdaGauss with BiCycAdaGauss · CUB-200 T=20 (ImageNet-pretrained)A_inc: 57.0 -> 55.9Hurt
replace AdaGauss with BiCycAdaGauss · CUB-200 T=20 (ImageNet-pretrained)A_last: 45.0 -> 43.7Hurt
replace AdaGauss with BiCycAdaGauss · CUB-200 T=10 (ImageNet-pretrained)A_inc: 63.4 -> 64.0Improved
replace AdaGauss with BiCycAdaGauss · CIFAR-100 T=10 (from scratch)F_last forgetting: 16.7 -> 13.5Improved
replace AdaGauss with BiCycAdaGauss · TinyImageNet T=20 (from scratch)F_last forgetting: 23.1 -> 18.9Improved

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