AI Paper Atlas

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

Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation

Linshan Wu, Zhun Zhong, Jiayi Ma, Yunchao Wei, Hao Chen, Leyuan Fang, Shutao Li A

TPAMI 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 34 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 L_self consistency between segmentation and GMM predictions (ablation)AGMM++ · PASCAL point-supervisedmIoU: 63.2 -> 72.0Improved
add L_weak (ablation)AGMM++ · PASCAL point-supervisedmIoU: 72.0 -> 74.5Improved
add L_con (ablation)AGMM++ · PASCAL point-supervisedmIoU: 74.5 -> 75.0Improved
add OEM optimization (ablation)AGMM++ · PASCAL point-supervisedmIoU: 75.0 -> 75.6Improved
add L_self (ablation)AGMM++ · PASCAL scribble-supervisedmIoU: 69.0 -> 73.2Improved
add OEM optimization (ablation)AGMM++ · PASCAL box-supervisedmIoU: 74.5 -> 75.5Improved
add OEM and redefined L_con over AGMM (ablation)AGMM++ · PASCAL point-supervisedmIoU: 69.6 -> 72.3Improved
add OEM and redefined L_con over AGMM (ablation)AGMM++ · PASCAL scribble-supervisedmIoU: 76.4 -> 77.5Improved
add L_self to pseudo-label generation over ToCo CAMs (ablation)AGMM++ · PASCAL image-level pseudo labelspseudo label mIoU: 70.5 -> 71.5Improved
add OEM to pseudo label generation (ablation)AGMM++ · PASCAL image-level pseudo labelspseudo label mIoU: 72.5 -> 73.3Improved
add stop-gradient to GMM (ablation)AGMM++ · PASCAL point-supervisedmIoU: 72.3 -> 67.4Hurt
use hard one-hot online labels instead of soft GMM labels (ablation)AGMM++ · PASCAL point-supervisedmIoU: 72.3 -> 66.5Hurt

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