Research map / Detection and segmentation / Weakly supervised detection and segmentation
DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision
Read the paperCheck 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 |
|---|---|---|---|
| refine pseudo-labels per method then fuse (DeepUSPS) versus prior deep unsupervised USD | DeepUSPS · MSRA-B | F-score: 87.70 -> 90.31 | Helped |
| DeepUSPS versus USD on ECSSD F-score | DeepUSPS · ECSSD | F-score: 87.83 -> 87.42 | Hurt |
| add inter-image consistency refinement to handcrafted maps before fusion (ablation) | DeepUSPS · MSRA-B | F-score: 84.57 -> 89.52 | Helped |
| add self-supervised iterative refinement (ablation) | DeepUSPS · MSRA-B | F-score: 89.52 -> 90.31 | Helped |
| add self-supervision to ECSSD (ablation) | DeepUSPS · ECSSD | F-score: 85.74 -> 87.42 | Helped |
| second self-supervision iteration on RBD maps (ablation) | DeepUSPS · MSRA-B | F-score: 87.10 -> 88.08 | Helped |
| replace DRN backbone with ResNet101 (ablation) | DeepUSPS · DUT | F-score: 73.58 -> 69.60 | Hurt |
| replace DRN backbone with ResNet101 (ablation) | DeepUSPS · MSRA-B | F-score: 90.31 -> 90.05 | No clear effect |
| oracle fusion with GT versus simple mean-loss fusion (ablation) | DeepUSPS · MSRA-B | F-score: 90.31 -> 91.34 | No clear effect |
Closest papers by meaning
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective (CVPR 2018 · similarity 0.93)
- Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning (AAAI 2022 · similarity 0.92)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.91)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.90)
- Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection (CVPR 2023 · similarity 0.90)
- Unsupervised Salient Instance Detection (CVPR 2024 · similarity 0.88)
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.