AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion

Chunming He, Rihan Zhang, Fengyang Xiao, Dingming Zhang, Zhiwen Cao, Sina Farsiu

ICML 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring 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 CurriSeg training to existing COD modelsFEDER, FSEL, RUN (ResNet50, Res2Net50, PVT V2) · COD benchmarksF-beta and composite gain: FEDER 0.715 -> 0.736 on COD10K F-beta; gains 2.13 to 3.94%Improved
add CurriSeg trainingRUN · COD training timetraining time (h): 12.64 -> 8.32Improved
add CurriSeg trainingRUN PVT V2 · CVC-ColonDBmDice: 0.822 -> 0.845Improved
add CurriSeg trainingRUN · GDD transparent objectsmIoU: 0.895 -> 0.902Improved
add warm-up curriculum alone, without uncertainty and temporal weighting (ablation)FEDER · COD10KF-beta: 0.715 -> 0.697Hurt
add pixel uncertainty weighting (PUE) on top of WCS (ablation)CurriSeg · COD10KF-beta: 0.697 -> 0.718Improved
add temporal statistics sample weighting (TSSW) (ablation)CurriSeg · COD10KF-beta: 0.718 -> 0.729Improved
add SBFT anti-curriculum phase after curriculum selection (ablation)CurriSeg · COD10KF-beta: 0.729 -> 0.736Improved
use SBFT alone without curriculum (ablation)FEDER · COD10KF-beta: 0.715 -> 0.723Improved
replace warm-up curriculum with self-paced learning or teacher-student curriculum (ablation)CurriSeg · COD10KF-beta: 0.738 and 0.735 vs 0.736No clear effect
use sqrt or squared warm-up schedule instead of linear p(t) (ablation)CurriSeg · COD10KF-beta: 0.730 and 0.726 vs 0.736Hurt
apply SBFT to all samples rather than only hard or random half (ablation)CurriSeg · COD10KF-beta: 0.730 / 0.728 -> 0.736Improved

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