Research map / Graph learning / Graph self-supervised learning
GraB: Visual Saliency via Novel Graph Model and Background Priors
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 |
|---|---|---|---|
| add boundary connections to the graph (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.756 | Helped |
| use RPCA-based boundary sampling (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.745 | Helped |
| use hierarchical saliency fusion (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.733 | Helped |
| use geodesic distance (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.730 | Helped |
| add erroneous boundary removal (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.725 | Helped |
| use simple multiscale averaging (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.725 | Helped |
| add relative-total-variation smoothing (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.716 | Helped |
| use CIELAB color histograms (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.716 | Helped |
| use mean CIELAB color features (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.715 | No clear effect |
| use Leung-Malik filter features (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.715 | No clear effect |
| use guided filtering (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.713 | No clear effect |
| use local binary pattern features (ablation) | GMR · ECSSD | F-Measure: 0.714 -> 0.610 | Hurt |
Closest papers by meaning
- Multi-scale Graph Fusion for Co-saliency Detection (AAAI 2021 · similarity 0.88)
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective (CVPR 2018 · similarity 0.88)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.87)
- A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking (NeurIPS 2024 · similarity 0.86)
- Unsupervised Salient Instance Detection (CVPR 2024 · similarity 0.85)
- Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks (CVPR 2024 · similarity 0.85)
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.