AI Paper Atlas

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

Partial Label Learning with Batch Label Correction

Yan Yan, Yuhong Guo

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 55 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 batch label correction (ablation)PL-BLC · Lostaccuracy: 0.616 -> 0.806Improved
add batch label correction (ablation)PL-BLC · Yahoo! Newsaccuracy: 0.529 -> 0.679Improved
add MixUp data enhancement (ablation)PL-BLC · Lostaccuracy: 0.741 -> 0.806Improved
add MixUp data enhancement (ablation)PL-BLC · Yahoo! Newsaccuracy: 0.674 -> 0.679Improved
add teacher consistency loss (ablation)PL-BLC · Lostaccuracy: 0.773 -> 0.806Improved
add teacher consistency loss (ablation)PL-BLC · BirdSongaccuracy: 0.706 -> 0.746Improved
add all three components over classification-only baseline (ablation)PL-BLC · Lostaccuracy: 0.562 -> 0.806Improved
add all three components over classification-only baseline (ablation)PL-BLC · Soccer Playeraccuracy: 0.470 -> 0.540Improved
add MixUp data enhancement (ablation)PL-BLC · Soccer Playeraccuracy: 0.537 -> 0.540No clear effect
use PL-BLC instead of SUREPL-BLC · MSRCv2accuracy: 0.481 -> 0.536Improved
increase consistency weight eta from 0.3-0.5 to >=1 (ablation)PL-BLC · Lost and MSRCv2accuracyHurt

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