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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add class-agnostic detector (CAD) trained on pseudo-boxes | LOST · VOC07 single-object discovery | CorLoc: 61.9 -> 65.7 | Improved |
| add class-agnostic detector (CAD) | LOST · VOC12 | CorLoc: 64.0 -> 70.4 | Improved |
| add class-agnostic detector (CAD) | LOST · COCO20k single-object discovery | CorLoc: 50.7 -> 57.5 | Improved |
| add class-agnostic detector (CAD) | TokenCut · VOC07 single-object discovery | CorLoc: 68.8 -> 71.4 | Improved |
| add class-agnostic detector (CAD) | MOVE · VOC07 single-object discovery | CorLoc: 76.0 -> 77.1 | Improved |
| add bilateral solver post-processing | TokenCut · DUT-OMRON unsupervised saliency detection | IoU: 53.3 -> 61.8 | Improved |
| add bilateral solver post-processing | LOST · DUT-OMRON unsupervised saliency detection | IoU: 41.0 -> 48.9 | Improved |
| train SelfMask segmenter on MOVE pseudo-masks | MOVE · DUT-OMRON unsupervised saliency detection | IoU: 61.5 -> 66.6 | Improved |
| train SelfMask segmenter on SEMPART pseudo-masks | SEMPART-fine · DUT-OMRON unsupervised saliency detection | IoU: 66.8 -> 69.8 | Improved |
| add bilateral solver post-processing | MOVE · DUT-OMRON unsupervised saliency detection | IoU: 61.5 -> 63.6 | Mixed |
| add learning of a task-specific model on pseudo-labels instead of training-free features | TokenCut · COCO20k single-object discovery | CorLoc: 58.8 -> 62.6 | Improved |
Closest papers by meaning
- Unsupervised Open-Vocabulary Object Localization in Videos (ICCV 2023 · similarity 0.92)
- Unsupervised Object Localization: Observing the Background To Discover Objects (CVPR 2023 · similarity 0.91)
- Unsupervised Object Localization with Representer Point Selection (ICCV 2023 · similarity 0.91)
- Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks (AAAI 2019 · similarity 0.88)
- Recognize Any Regions (NeurIPS 2024 · similarity 0.87)
- Unsupervised Object Detection with Theoretical Guarantees (NeurIPS 2024 · similarity 0.87)
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.
