AI Paper Atlas

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

AES: Curing Optimizer Blindness in Long-Tailed Recognition via State-Aware Correction

Fanfu Wang, Jiachang Zhan, Zhiheng Gong, Pengkun Wang, Yang Wang

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training

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 SCAF (ablation)AES · CIFAR-100-LT (IR=100)top-1 accuracy (All): 56.77 -> 57.85Improved
add E-PCG (ablation)AES · CIFAR-100-LT (IR=100)top-1 accuracy (All): 57.26 -> 57.85Improved
add ARS (ablation)AES · CIFAR-100-LT (IR=100)top-1 accuracy (All): 57.00 -> 57.85Improved
add ARS (ablation)AES · CIFAR-100-LT (IR=100)Tail accuracy: 37.90 -> 34.33Hurt
add SCAF (ablation)AES · CIFAR-100-LT (IR=100)Head accuracy: 78.17 -> 79.23Improved
replace TS-MOF with AESTS-MOF · CIFAR-100-LT (IR=50)top-1 accuracy: 60.2 -> 63.0Improved
replace TS-MOF with AESTS-MOF · ImageNet-LTtop-1 accuracy: 56.3 -> 57.4Improved
replace TS-MOF with AESTS-MOF · iNaturalist 2018top-1 accuracy: 72.3 -> 73.8Improved
replace TS-MOF with AESTS-MOF · ImageNet-LT Tailtop-1 accuracy: 42.6 -> 40.4Hurt
replace TS-MOF with AESTS-MOF · CIFAR-100-LT (IR=100) Tailtop-1 accuracy: 39.9 -> 33.9Hurt
replace TS-MOF with AESTS-MOF · CIFAR-100-LT (IR=100) Mediumtop-1 accuracy: 49.2 -> 56.9Improved
replace TS-MOF with AESTS-MOF · blindness coefficientbeta: 0.1784 -> 0.1163Improved

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