AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization

Zitai Wang, Qianqian Xu, Zhiyong Yang, Zhi Qiang Xu, Linchao Zhang, Xiaochun Cao, Qingming Huang

TPAMI 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 8 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 ADRW re-weighting to CVS (ablation)CVS · CIFAR-100 LT (rho=100, protocol a)balanced accuracy: 43.5 -> 44.4Improved
add ADRW re-weighting to CVS (ablation)CVS · CIFAR-100 LT (rho=100, all classes, PEFT ViT)balanced accuracy: 79.9 -> 80.3Improved
add ADRW re-weighting to CVS (ablation)CVS · CIFAR-10 LT (rho=100, protocol a)balanced accuracy: 81.3 -> 81.5Improved
add ADRW re-weighting to CE (ablation)CE · CIFAR-10 LT (rho=100, protocol a)balanced accuracy: 71.5 -> 78.6Improved
add ADRW re-weighting to CE (ablation)CE · CIFAR-100 LT (rho=100, protocol a)balanced accuracy: 38.3 -> 41.8Improved
add DRW re-weighting to VS (ablation)VS · CIFAR-100 LT (rho=100, protocol a)balanced accuracy: 41.8 -> 41.3Hurt
add DRW to VS (ablation)VS · CIFAR-10 LT (rho=100, protocol a)balanced accuracy: 78.8 -> 80.1Improved
use CVS loss instead of VS+TLA+ADRW (conference version)VS+TLA+ADRW · CIFAR-100 LT (rho=100, protocol b tuned wd)balanced accuracy: 46.3 -> 48.2Improved
tune weight decay (protocol b instead of a) (ablation)VS · CIFAR-100 LT (rho=100)balanced accuracy: 41.8 -> 46.3Improved
use CVS+ADRW instead of VSVS · CIFAR-100 LT (rho=100, all classes, FFT ViT)balanced accuracy: 79.1 -> 80.0Improved
use CVS instead of VS (ablation)VS · ImageNet-LT (ResNet-50)balanced accuracy: 54.1 -> 54.7Improved
use CVS instead of Origin (ablation)Ours-Origin · iNaturalist (ResNet-50)balanced accuracy: 70.7 -> 71.5Improved

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