Research map / Detection and segmentation / CNN features
Unconstrained Salient Object Detection via Proposal Subset Optimization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use MAP subset optimization instead of greedy NMS | SalCNN · MSO | AP: .654 -> .734 | Helped |
| Use MAP subset optimization instead of greedy NMS | SalCNN · DUT-O | AP: .432 -> .510 | Helped |
| Use MAP subset optimization instead of greedy NMS | SalCNN · MSRA | AP: .722 -> .778 | Helped |
| Use MAP subset optimization instead of greedy NMS | SalCNN · VOC07 | AP: .300 -> .337 | Helped |
| Add adaptive region sampling (ablation) | SalCNN · MSO overall | AP: .504 -> .734 | Helped |
| Add adaptive region sampling (ablation) | SalCNN · MSO single-object images | AP: .676 -> .818 | Helped |
| Replace adaptive with uniform region sampling (ablation) | SalCNN · MSO large-object images | AP: .859 -> .726 | Hurt |
| Replace adaptive with uniform region sampling (ablation) | SalCNN · MSO multiple-object images | AP: .698 -> .540 | Helped |
| Use MAP filtering instead of score thresholding (ablation) | SalCNN · MSO overall | AP: .654 -> .734 | Helped |
| Use MAP filtering instead of MMR (ablation) | SalCNN · MSO overall | AP: .656 -> .734 | Helped |
| Use MAP filtering instead of rank thresholding (ablation) | SalCNN · MSO single-object images | AP: .717 -> .818 | Helped |
| Use MAP filtering instead of score thresholding (ablation) | SalCNN · MSO large-object images | AP: .833 -> .859 | Helped |
Closest papers by meaning
- What Is and What Is Not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors (CVPR 2017 · similarity 0.89)
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 2018 · similarity 0.88)
- Locate Globally, Segment Locally: A Progressive Architecture With Knowledge Review Network for Salient Object Detection (AAAI 2021 · similarity 0.88)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.88)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.88)
- Exploring Salient Object Detection with Adder Neural Networks (AAAI 2025 · similarity 0.86)
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.