AI Paper Atlas

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

Label-Guided Representation Learning for Incomplete Multi-View Multi-Label Classification

Yang Li, Quanjiang Li, Tingjin Luo

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Incomplete multi-view multi-label learning

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 category-specific conditional posteriors in fusion (ablation)LGRL · Corel5kAP: 0.446 -> 0.469Improved
add category-specific conditional posteriors in fusion (ablation)LGRL · Pascal07AP: 0.548 -> 0.607Improved
add category-specific conditional posteriors in fusion (ablation)LGRL · OBJECTAP: 0.635 -> 0.705Improved
add category-specific conditional posteriors in fusion (ablation)LGRL · MirflickrAP: 0.608 -> 0.653Improved
add task-relevant consistency constraints (ablation)LGRL · Corel5kAP: 0.455 -> 0.469Improved
add task-relevant consistency constraints (ablation)LGRL · Pascal07AP: 0.582 -> 0.607Improved
add semantic alignment loss (ablation)LGRL · Corel5kAP: 0.464 -> 0.469Improved
add semantic alignment loss (ablation)LGRL · Pascal07AP: 0.586 -> 0.607Improved
add semantic alignment loss (ablation)LGRL · OBJECTAP: 0.680 -> 0.705Improved
vary lambda and beta between 0.1 and 1 (ablation)LGRL · Corel5k, OBJECTAPNo 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