AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Annotation-Efficient Coreset Selection for Context-dependent Segmentation

Jin Zhang, Zhe Cao, Biwen Yang, Ruiheng Zhang

CVPR 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport

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
use point-based optimal-transport cost with MDE instead of fully supervised scoring (TFDP)CostSet · SOD (DUTS), 80% pruningIoU: 62.1 -> 66.2Improved
use CostSet at 40% pruning versus full dataUNet ResNet50 · COD (COD10K)IoU: 55.1 -> 52.0Hurt
use CostSet on TOD where gains are smallerCostSet · TOD (GDD), 80% pruningIoU: 64.8 -> 65.6 (vs CCS)Improved
add MDE selection instead of TopK on ADP cost (ablation)CostSet · SOD (DUTS), 80% pruningIoU: 64.4 -> 66.2Improved
add MDE selection instead of TailK on ADP cost (ablation)CostSet · SOD (DUTS), 80% pruningIoU: 63.1 -> 66.2Improved
add MDE selection instead of TopK at low pruning (ablation)CostSet · SOD (DUTS), 10% pruningIoU: 74.9 -> 74.8No clear effect
use MDE instead of CCS/Entropy/EL2N/Forgetting/TFDP on same transport cost (ablation)CostSet · SOD (DUTS), 80% pruningIoU: 64.3 -> 66.2 (vs CCS)Improved
use transport cost C scoring in other selection methods versus their original scores (ablation)Entropy/Forgetting/EL2N/CCS/TFDP · SOD (DUTS)IoU: e.g. CCS +6.3 at 80%, TFDP +0.8Improved
replace point labels by GT pixel-level cost (ablation)CostSet · SOD (DUTS)IoU: 66.2 -> 66.9 (80%)No clear effect
use box or scribble labels instead of points in ADP (ablation)CostSet · SOD (DUTS)IoU across pruning rates: label time 2s -> 6s (box)No clear effect
use point labels instead of boxes (ablation)ADP · SOD (DUTS)background coverage Bc: 15.7% -> 8.3%Improved
tune drop ratio per task (0.15 for SOD/MIS, 0.1 for others) (ablation)MDE · six CD tasksIoUMixed

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