AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Learn from All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition

Yuhang Zhang, Chengrui Wang, Xu Ling, Weihong Deng

ECCV 2022 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 283 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 flip attention consistency (ablation)EAC (erasing + imbalanced framework) · RAF-DB (30% label noise)accuracy (%): 78.10 -> 84.42Improved
add the imbalanced framework (ablation)EAC · RAF-DB (30% label noise)accuracy (%): 78.29 -> 84.42Improved
add random erasing (ablation)EAC · RAF-DB (30% label noise)accuracy (%): 76.26 -> 84.42Improved
use flip instead of rotate as the spatial transform (ablation)EAC · RAF-DB (30% label noise)accuracy (%): 78.23 -> 84.42Improved
use flip instead of scale as the spatial transform (ablation)EAC · RAF-DB (30% label noise)accuracy (%): 82.01 -> 84.42Improved
use erasing instead of blur (ablation)EAC · RAF-DB (30% label noise)accuracy (%): 76.92 -> 84.42Improved
use erasing instead of AutoAugment (ablation)EAC · RAF-DB (30% label noise)accuracy (%): 82.40 -> 84.42Improved
add EAC to MobileNetMobileNet · RAF-DB (30% label noise)accuracy (%): 62.48 -> 79.82Improved
add EAC to ResNet-50ResNet-50 · RAF-DB (30% label noise)accuracy (%): 71.67 -> 85.27Improved
use EAC instead of RULResNet-18 noisy FER · RAF-DB (30% label noise)accuracy (%): 82.06 -> 84.42Improved
use EAC instead of baselineResNet-18 on Tiny-ImageNet · Tiny-ImageNet (30% label noise)top-1 accuracy (%): 41.32 -> 63.51Improved
use EAC instead of KTN on clean FERPlusResNet-18 · FERPlus (clean)accuracy (%): 90.49 -> 89.64Hurt

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