AI Paper Atlas

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

Facial Expression Recognition with Inconsistently Annotated Datasets

Jiabei Zeng, Shiguang Shan, Xilin Chen

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 362 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
replace probability transition layers with a category-general fully connected layer (e2e-fc) (ablation)IPA2LT(LTNet) · FER overall averageaccuracy: 70.64 -> 28.87Hurt
add probability transition layers (end-to-end latent truth) instead of two-step EM then CNN (ablation)IPA2LT · FER overall averageaccuracy: 68.53 -> 70.64Improved
use end-to-end LTNet instead of EM+CNN (spectral init) (ablation)LTNet · CIFAR-10 noisy labelsaccuracy: 78.82 -> 87.23Improved
use all three inconsistent label sets instead of a single noisy setbasic CNN · CIFAR-10 noisy labelsaccuracy: 62.50 -> 84.04Improved
model each coder's annotation bias with LTNet instead of mixing labels in a CNN (ablation)basic CNN on mixture · CIFAR-10 noisy labelsaccuracy: 84.04 -> 87.23Improved
use LTNet instead of NALIPA2LT · FER overall averageaccuracy: 70.15 -> 70.64Improved
use LTNet instead of AIRIPA2LT · FER overall averageaccuracy: 55.21 -> 70.64Improved
add LTNet with predicted annotations from unlabeled data to AffTr+RAFTr trainingbase ResNet-80 · FER overall averageaccuracy: 69.77 -> 70.64Improved
LTNet vs NAL on AffectNetIPA2LT · AffectNet valaccuracy: 55.97 -> 55.11Mixed

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