AI Paper Atlas

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

Contrastive Adversarial Learning for Person Independent Facial Emotion Recognition

Daeha Kim, Byung Cheol Song

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 32 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 contrastive adversarial learning with ResNet18FER on AffectNet · AffectNetRMSE (valence): 0.2668 -> 0.2186Improved
add contrastive adversarial learning with ResNet18FER on AFEW-VA · AFEW-VARMSE (valence): 0.24 -> 0.17Improved
add contrastive adversarial learning with ResNet18FER on Aff-Wild · Aff-WildCCC (arousal): 0.31 -> 0.56Improved
replace the CAF critic loss with generic adversarial learning (ablation)ResNet18 FER on AffectNet · AffectNetRMSE (valence): 0.2186 -> 0.3687Hurt
replace the CAF critic loss with FisherGAN (ablation)ResNet18 FER on AffectNet · AffectNetRMSE (valence): 0.2186 -> 0.2221Hurt
replace the CAF critic loss with SphereGAN (ablation)ResNet18 FER on AffectNet · AffectNetRMSE (valence): 0.2186 -> 0.2467Hurt
replace the CAF critic loss with GramNet (ablation)ResNet18 FER on AffectNet · AffectNetRMSE (valence): 0.2186 -> 0.2251Hurt
use a constant instead of the adaptive margin interval (ablation)ResNet18 CAF on AffectNet · AffectNetRMSE (valence): 0.2186 -> 0.2289Hurt
use a constant instead of the adaptive margin interval (ablation)ResNet18 CAF on AffectNet · AffectNetRMSE (arousal): 0.1873 -> 0.2082Hurt
use a linear model instead of the adaptive margin interval (ablation)ResNet18 CAF on AffectNet · AffectNetRMSE (valence): 0.2186 -> 0.2201Hurt
use a linear model instead of the adaptive margin interval (ablation)ResNet18 CAF on AffectNet · AffectNetRMSE (arousal): 0.1873 -> 0.1982Hurt
replace Otsu grouping with k-means grouping (ablation)CAF on AffectNet · AffectNetRMSE: about 0.05No clear effect

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