AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation

Sanghyun Jo, Seo Jin Lee, Seungwoo Lee, Seohyung Hong, Hyungseok Seo, Kyungsu Kim

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic 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 unsupervised semantic segmentation (USS) propagation (ablation)SSA baseline · MoNuSeg trainFN rate: 0.536 -> 0.020Improved
add USS propagation without OT (ablation)SSA baseline · MoNuSeg trainFP rate: 0.159 -> 0.552Hurt
add optimal transport after USS propagation (ablation)USS propagation · MoNuSegFP rate: 0.552 -> 0.303Improved
replace GMM clustering with optimal transport (ablation)USS + clustering · MoNuSeg testIoU: 0.482 -> 0.539Improved
add CRF after USS (ablation)USS propagation · MoNuSegIoU: 0.439 -> 0.443No clear effect
add watershed post-processing (ablation)USS + OT + CRF · MoNuSeg trainAJI: 0.001 -> 0.380Improved
add instance-level scored self-distillation (ablation)SSA baseline · MoNuSeg testAJI: 0.259 -> 0.386Improved
add pixel-level cell propagation on top of scored distillation (ablation)COIN · MoNuSeg testAJI: 0.386 -> 0.580Improved
add instance propagation without scored distillation (ablation)SSA baseline · MoNuSeg testAJI: 0.259 -> 0.260No clear effect
use SAM masks as pseudo-GT without confidence scoring (ablation)SSA baseline · MoNuSeg testAJI: 0.259 -> 0.000Hurt
add instance-level confidence scoring to SAM pseudo labels (ablation)SSA + SAM · MoNuSeg testAJI: 0.000 -> 0.580Improved
add edge decoder (ablation)COIN (SSA) · MoNuSeg test adjacent cellsAJI: 0.493 -> 0.528Improved

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