AI Paper Atlas

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

SCDL: Synergistic Confidence-Dispersion Learning for Semi-Supervised Video Polyp Segmentation

Yuanqin he, Yuhua Zhang, Huisi Wu, Jing Qin

ECCV 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical 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 PAR to baseline (ablation)Baseline · SUN-SEG Hard 1/2Dice: 80.21 -> 82.36Improved
add SCOS to PAR (ablation)SCDL · SUN-SEG Hard 1/2Dice: 82.36 -> 83.72Improved
add CCP to PAR+SCOS (ablation)SCDL · SUN-SEG Hard 1/2Dice: 83.72 -> 84.28Improved
add PAR to SCOS+CCP (ablation)SCDL · SUN-SEG Hard 1/2Dice: 83.24 -> 84.28Improved
add PAR to SCOS+CCP at 1/16 labels (ablation)SCDL · SUN-SEG Hard 1/16Dice: 80.32 -> 81.66Improved
add CCP to PAR+SCOS at 1/16 labels (ablation)SCDL · SUN-SEG Hard 1/16Dice: 81.13 -> 81.66Improved
add IOF to PAR (ablation)PAR · SUN-SEG Hard 1/2Dice: 83.24 -> 83.64Improved
add EOF to IOF (ablation)PAR · SUN-SEG Hard 1/2Dice: 83.64 -> 83.92Improved
add OPG to IOF+EOF (ablation)PAR · SUN-SEG Hard 1/2Dice: 83.92 -> 84.28Improved
use cosine instead of Euclidean distance in k-means (ablation)OPG · SUN-SEG Hard 1/2Dice: 81.74 -> 84.28Improved
use 5 prototypes instead of 3 (ablation)OPG · SUN-SEG Hard 1/2Dice: 82.06 -> 84.28Improved
use 5 prototypes instead of 7 (ablation)OPG · SUN-SEG Hard 1/2Dice: 82.43 -> 84.28Improved

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