AI Paper Atlas

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

Label Error Correction and Generation through Label Relationships

Zijun Cui, Yong Zhang, Qiang Ji

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 23 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
train on MAP-corrected labels instead of original noisy labels (LR)logistic regression · CK+ AU recognitionmean F1-score: 0.785 -> 0.830Improved
train on MAP-corrected labels (LR)logistic regression · BP4D AU recognitionmean F1-score: 0.657 -> 0.687Improved
train on corrected labels (LR, missing labels completed)logistic regression · EmotionNet AU recognitionmean F1-score: 0.491 -> 0.524Improved
train on corrected labels (CNN)3-layer CNN · EmotionNet AU recognitionmean F1-score: 0.620 -> 0.626Improved
train on corrected labelslinear SVM · a-Pascal attribute predictionG-Mean: 0.743 -> 0.753Improved
train on corrected labelsMLTSVM · CK+ AU recognitionmean F1-score: 0.691 -> 0.784Improved
generate labels for MMI from relationships learned on CK+SVM · MMI AU recognitionmean F1-score: 0.482 -> 0.532Improved
remove object-level (expression) labels from label relationships (AUs only) (ablation)MAPLB with LR · CK+ AU recognitionmean F1-score: 0.830 -> 0.809Hurt
use AU-only relationships to correct labels vs original labels (ablation)LR · CK+ AU recognitionmean F1-score: 0.785 -> 0.809Improved
train on corrected labelsLR · CK+ AU prediction uncertaintymean entropy: 0.194 -> 0.110Improved
use corrected labels for AU-to-expression pipelineLR · CK+ expression recognitionaccuracy: 0.820 -> 0.885Improved

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