AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation

Runlong Cao, Ying Zang, Chuanwei Zhou, Tianrun Chen, Tong Zhang, Zhen Cui, Chunyan Xu

ICML 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 0 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 SPM uncertainty-aware prior fusion (ablation)semi-supervised baseline · RefCOCO val 5% labelsoverall IoU: 58.23 -> 65.73Improved
add SESM guidance on top of SPM (ablation)L2L · RefCOCO val 5% labelsoverall IoU: 65.73 -> 66.99Improved
add RPLE on top of SPM+SESM (ablation)L2L · RefCOCO val 5% labelsoverall IoU: 66.99 -> 67.30Improved
use learned stage-wise gating instead of fixed 0.5/0.5 weighting in SESM (ablation)SESM · RefCOCO val 5% labelsoverall IoU: 67.04 -> 67.30Improved
use projection in shallow stages and attention in deep stages instead of all attention (ablation)SESM structural stream · RefCOCO val 5% labelsoverall IoU: 65.08 -> 67.30Improved
use attention in all four stages instead of projection in all four (ablation)SESM structural stream · RefCOCO val 5% labelsoverall IoU: 66.92 -> 65.08Hurt
add consistency gain to RPLE reward (ablation)RPLE · RefCOCO val 5% labelsoverall IoU: 65.36 -> 67.30Improved
add coverage gain to RPLE reward (ablation)RPLE · RefCOCO val 5% labelsoverall IoU: 65.95 -> 67.30Improved
add separability gain to RPLE reward (ablation)RPLE · RefCOCO val 5% labelsoverall IoU: 66.35 -> 67.30Improved
replace RPLE adaptive thresholds with static foreground threshold (ablation)L2L · RefCOCO val 5% labelsoverall IoU: tau 0.7: 66.99; tau 0.8: 66.31 vs RPLE 67.30Mixed
increase SPM coefficients kappa_w or kappa_a (ablation)SPM · RefCOCO valoverall IoU: 67.30 -> 65.96 at worstNo clear effect
use MLLM+SAM2 priors with naive 0.5 linear fusion vs no MLLMsemi-supervised baseline · RefCOCO val 0.1% labelsoverall IoU: 21.72 -> 62.25Improved

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