AI Paper Atlas

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

Norface: Improving Facial Expression Analysis by Identity Normalization

Hanwei Liu, Rudong An, Zhimeng Zhang, Bowen Ma, Wei Zhang, Yan Song, Yujing Hu, Chen Wei, Yu Ding

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 22 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 identity normalization (normalized images as extra input) (ablation)Norface classification network · BP4D AU detectionF1: 67.2 -> 69.3Improved
add identity normalization (ablation)Norface · RAF-DBaccuracy: 89.24 -> 92.97Improved
add identity normalization (ablation)Norface · AffectNetaccuracy: 67.29 -> 68.69Improved
use identity normalization instead of mixup/cutout/cutmix augmentation (ablation)Norface · BP4D AU detectionF1: 67.4 (CutMix) -> 69.3Improved
standard augmentation (mixup, cutout, cutmix) vs random init (ablation)Norface baseline · BP4D+ AU detectionF1: 64.0 -> 64.2 to 64.8No clear effect
feed expression features instead of normalized images to classifier (ablation)Norface · BP4D AU detectionF1: 69.3 -> 67.1Hurt
add Input and Output MoE modules (ablation)Norface classification network · BP4D AU detectionF1: 65.9 -> 69.3Improved
add Input MoE (vs only Output MoE) (ablation)Norface · RAF-DBaccuracy: 92.57 -> 92.97Improved
add importance loss (ablation)Norface MoE · RAF-DBaccuracy: 91.66 -> 92.97Improved
add eyebrow loss to expression loss in normalization network (ablation)normalization network · AU detection (eyebrow regions)F1: +0.5% averageImproved
increase number of experts up to m=4 (ablation)Norface MoE · AU detection and FERF1 / accuracy: +3.0% and +5.74% vs m=0Improved
choose a poor target identity (ID3 vs ID6) (ablation)Idn target face · BP4D AU detectionF1: -1.1%Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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