AI Paper Atlas

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

LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise

Zhiyu Wu, Jinshi Cui

ICCV 2023 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 56 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 label distribution estimation using expression space only (ablation)LA-Net baseline · RAF-DB (30% noise)accuracy (%): 75.50 -> 79.17Improved
add landmark information to label distribution estimation (ablation)LA-Net · RAF-DB (30% noise)accuracy (%): 79.17 -> 82.37Improved
add landmark information to label distribution estimation (ablation)LA-Net · RAF-DB (original)accuracy (%): 88.43 -> 89.04Improved
add expression-landmark contrastive loss with one-hot labels (ablation)LA-Net (LD+LM) · RAF-DB (original)accuracy (%): 89.04 -> 90.48Improved
use pseudo-labels in EL Loss pair selection instead of one-hot labels (ablation)LA-Net · RAF-DB (30% noise)accuracy (%): 83.21 -> 85.33Improved
use pseudo-labels in EL Loss pair selection instead of one-hot labels (ablation)LA-Net · RAF-DB (original)accuracy (%): 90.48 -> 90.81Improved
vary number of neighbors K (K=12 vs 8) (ablation)LA-Net · RAF-DB original vs 30% noiseaccuracy (%)Mixed
replace EAC with LA-Net under label noiseFER noise-tolerant models · AffectNet (10%/20%/30% noise)accuracy (%): 58.91 -> 60.82 at 30% noiseImproved
apply LA-Net instead of baseline at 30% noiseResNet-18 · AffectNet (30% noise)accuracy (%): 52.16 -> 60.82Improved
train on mixed RAF-DB and AffectNet with inconsistent labels using LA-Net instead of LDLVAFER cross-dataset · AffectNet 7-classaccuracy (%): 62.89 -> 65.43Improved
LA-Net label distributions instead of one-hot labels as descriptorFER annotation · AffectNet user studyJS divergence to human perception: 0.2030 -> 0.0909Improved
replace TransFER with LA-Net (ResNet-18) on RAF-DB originalFER · RAF-DB (original)accuracy (%): 90.91 vs 90.81No clear effect

Later papers that compared with this method

3 later accepted papers report LA-Net as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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