AI Paper Atlas

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

SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics

Sriram Ravindran, Debraj Basu

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 5 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 jointly optimized fine branch with coarse branch (ablation)Sempart · DUT-OMRON saliencymIoU: 0.662 -> 0.668Improved
add coarse branch to a fine-only model (ablation)Sempart · DUT-OMRON saliencymIoU: 0.645 -> 0.668Improved
add graph TV regularization on fine mask (ablation)Sempart · DUT-OMRON saliencymIoU: 0.637 -> 0.668Improved
add graph TV regularization on coarse mask (ablation)Sempart · DUT-OMRON saliencymIoU: 0.646 -> 0.668Improved
add graph TV coarse loss (ablation)Sempart · DUTS-TE saliencymIoU: 0.749 -> 0.749No clear effect
remove self-loops from affinity matrix (ablation)Sempart · DUT-OMRON saliencymIoU: 0.667 -> 0.668Improved
select foreground by least-corners rule (ablation)Sempart · ECSSD saliencymIoU: 0.825 -> 0.855 (vs framing prior)Improved
apply bilateral filtering after inference (ablation)Sempart-Fine · DUT-OMRON saliencyIoU: 0.668 -> 0.653Hurt
train SelfMask on Sempart masksSempart-Fine · DUT-OMRON saliencyIoU: 0.668 -> 0.698Improved
train SelfMask on Sempart masksSempart-Fine · ECSSD saliencyIoU: 0.855 -> 0.850Hurt
use smaller patch size (ViT-S/8 instead of ViT-S/16) in DINO backbone (ablation)Sempart-Fine · DUT-OMRON saliencyIoU: 0.596 -> 0.668Improved
use fine mask instead of coarse mask (ablation)Sempart · DUT-OMRON saliencyIoU: 0.640 -> 0.668Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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