AI Paper Atlas

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

When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation

Pan Liu, Jinshi Liu

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 13 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 residual dispersion and optimized selection (M_i) to semi-supervised baseline (ablation)SemiBaseline · PASCAL VOC original 1/16mIoU: 72.9 -> 73.8Improved
add residual dispersion and optimized selection (M_i) to semi-supervised baseline (ablation)SemiBaseline · PASCAL VOC original 1/2mIoU: 78.6 -> 79.3Improved
add smooth loss weight on top of M_i (ablation)CSL · PASCAL VOC original 1/16mIoU: 73.8 -> 74.2Improved
add smooth loss weight on top of M_i (ablation)CSL · PASCAL VOC original 1/2mIoU: 79.3 -> 79.8Improved
add reliable-pixel masking loss on top of M_i and smooth weights (ablation)CSL · PASCAL VOC original 1/16mIoU: 74.2 -> 76.8Improved
add reliable-pixel masking loss on top of M_i and smooth weights (ablation)CSL · PASCAL VOC original 1/2mIoU: 79.8 -> 80.9Improved
compute pseudo-label selection on labeled plus unlabeled data (D_l U D_u) instead of unlabeled only (ablation)CSL · PASCAL VOC original 1/16mIoU: 76.8 -> 75.6Hurt
use class-specific CSL instead of class-agnostic (ablation)CSL · PASCAL VOC original 1/16mIoU: 76.8 -> 74.6Hurt
combine all four metrics (v_n, entropy, residual entropy, margin) instead of confidence plus residual dispersion (ablation)CSL · PASCAL VOC original 1/8mIoU: 79.6 -> 71.5Hurt
add residual entropy as extra metric (ablation)CSL · PASCAL VOC original 1/8mIoU: 79.6 -> 77.3Hurt
add margin as extra metric (ablation)CSL · PASCAL VOC original 1/8mIoU: 79.6 -> 76.9Hurt
use loss weights lambda1=1.00, lambda2=1.00 instead of 0.50/0.50 (ablation)CSL · PASCAL VOC original 1/16mIoU: 76.8 -> 72.5Hurt

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