AI Paper Atlas

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

Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey

Oriane Siméoni, Éloi Zablocki, Spyros Gidaris, Gilles Puy, Patrick Pérez

IJCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 18 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 class-agnostic detector (CAD) trained on pseudo-boxesLOST · VOC07 single-object discoveryCorLoc: 61.9 -> 65.7Improved
add class-agnostic detector (CAD)LOST · VOC12CorLoc: 64.0 -> 70.4Improved
add class-agnostic detector (CAD)LOST · COCO20k single-object discoveryCorLoc: 50.7 -> 57.5Improved
add class-agnostic detector (CAD)TokenCut · VOC07 single-object discoveryCorLoc: 68.8 -> 71.4Improved
add class-agnostic detector (CAD)MOVE · VOC07 single-object discoveryCorLoc: 76.0 -> 77.1Improved
add bilateral solver post-processingTokenCut · DUT-OMRON unsupervised saliency detectionIoU: 53.3 -> 61.8Improved
add bilateral solver post-processingLOST · DUT-OMRON unsupervised saliency detectionIoU: 41.0 -> 48.9Improved
train SelfMask segmenter on MOVE pseudo-masksMOVE · DUT-OMRON unsupervised saliency detectionIoU: 61.5 -> 66.6Improved
train SelfMask segmenter on SEMPART pseudo-masksSEMPART-fine · DUT-OMRON unsupervised saliency detectionIoU: 66.8 -> 69.8Improved
add bilateral solver post-processingMOVE · DUT-OMRON unsupervised saliency detectionIoU: 61.5 -> 63.6Mixed
add learning of a task-specific model on pseudo-labels instead of training-free featuresTokenCut · COCO20k single-object discoveryCorLoc: 58.8 -> 62.6Improved

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