AI Paper Atlas

Research map / Continual learning / Class-incremental

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

Hongye Xu, Bartosz Krawczyk

ECCV 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
add topology-aware evolution (adapter learned in primary training) (ablation)GATF · CIFAR-100 (from scratch, T=10)A_last: 46.8 -> 50.3Improved
add Analytic Geometric Anchor on top of topology-aware (ablation)GATF · CIFAR-100 (from scratch, T=10)A_last: 50.3 -> 51.7Improved
remove post-hoc refinement (end-to-end only) (ablation)GATF · CIFAR-100 (from scratch, T=10)A_last: 51.7 -> 52.0Improved
remove post-hoc refinement (ablation)GATF · TinyImageNet T=20A_last: 31.7 -> 31.5Hurt
add AGA to topology-aware model (ablation)GATF · TinyImageNet T=10A_last: 35.6 -> 37.0Improved
use GATF instead of DPCRGATF vs DPCR · CIFAR-100 T=10A_last: 50.2 -> 52.0Improved
use GATF instead of AdaGaussGATF vs AdaGauss · ImageNet-100 T=20A_last: 42.6 -> 44.7Improved
use GATF instead of LDCGATF vs LDC · ImageNet-100 T=10A_inc: 69.4 -> 67.4Hurt
use GATF with pretrained backboneGATF vs EFC/AdaGauss · CUB-200A_last: T=10: 52.9 (AdaGauss) vs 52.4; T=20: 46.1 (EFC) vs 43.7No clear effect

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