AI Paper Atlas

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

S4M: Boosting Semi-Supervised Instance Segmentation with SAM

Heeji Yoon, Heeseong Shin, Eunbeen Hong, Hyunwook Choi, Hansang Cho, Daun Jeong, Seungryong Kim

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 7 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 structural distillation loss from SAM to the teacher (ablation)Mask2Former teacher · Cityscapes 5% labeledmask AP: 14.9 -> 17.2Improved
add structural distillation loss from SAM to the teacher (ablation)Mask2Former teacher · Cityscapes 10% labeledmask AP: 19.0 -> 22.5Improved
add structural distillation loss from SAM to the teacher (ablation)Mask2Former teacher · COCO 10% labeledmask AP: 30.1 -> 30.3No clear effect
apply structural distillation to teacher only (ablation)S4M · Cityscapes 10% labeledmask AP: 30.1 -> 32.8Improved
also apply structural distillation to the student (ablation)S4M with teacher SD · Cityscapes 10% labeledmask AP: 32.8 -> 29.4Hurt
distill SAM decoder features instead of encoder features (ablation)teacher structural distillation · Cityscapes 10% labeledmask AP: 21.4 -> 22.4Improved
use structural loss instead of feature distillation (ablation)teacher distillation from SAM encoder · Cityscapes 10% labeledmask AP: 21.1 -> 21.4Improved
add pseudo-label refinement with SAM (ablation)S4M with SD · Cityscapes 10% labeledmask AP: 29.2 -> 32.3Improved
add augmentation with refined pseudo-labels (ARP) alone (ablation)baseline student · Cityscapes 10% labeledmask AP: 28.4 -> 27.8Hurt
add ARP on top of SD and pseudo-label refinement (ablation)S4M · Cityscapes 10% labeledmask AP: 32.3 -> 32.8Improved
use K sampled points instead of a single point prompt for SAM refinement (ablation)S4M · Cityscapes 10% labeledmask AP: 30.4 -> 32.8Improved
use K sampled points instead of mask prompt for SAM refinement (ablation)S4M · Cityscapes 10% labeledmask AP: 24.3 -> 32.8Improved

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