AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Generalizable Facial Expression Recognition

Yuhang Zhang, Xiuqi Zheng, Chenyi Liang, Jiani Hu, Weihong Deng

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 29 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
learn sigmoid masks on fixed CLIP face features (ablation)CAFE (ResNet-18) · Train RAF-DB, mean over four unseen test setsmean accuracy: 46.67 -> 55.49Improved
add channel-separation module (per-class channel groups, no FC) (ablation)CAFE · Train RAF-DB, mean over four unseen test setsmean accuracy: 55.49 -> 56.80Improved
add channel-diverse loss (ablation)CAFE · Train RAF-DB, mean over four unseen test setsmean accuracy: 56.80 -> 57.17Improved
apply sigmoid to learned masks (ablation)CAFE · Train RAF-DB, mean over five test setsmean accuracy: 58.05 -> 63.48Improved
apply sigmoid mask: effect on source domain RAF-DB (ablation)CAFE · Train RAF-DB, test RAF-DB (source)accuracy: 89.24 -> 88.72Mixed
use CAFE mask design instead of fine-tuning FC on concatenated CLIP features (ablation)CLIP + FER model · Train RAF-DB, mean over five test setsmean accuracy: 55.73 -> 63.48Improved
add CAFE to different backbones (ablation)MobileNet · Train RAF-DB, mean over five test setsmean accuracy: 54.66 -> 56.30Improved
add CAFE to ResNet-50 (ablation)ResNet-50 · Train RAF-DB, mean over five test setsmean accuracy: 60.98 -> 64.07Improved
stronger source-domain FER methods (EAC, OFER) versus older SCNFER baselines · Train RAF-DB, test FERPlusaccuracy: 58.37 (SCN) -> 54.38 (EAC), 53.90 (OFER)Hurt

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