Research map / Detection and segmentation / CNN features
Salient Object Detection With Pyramid Attention and Salient Edges
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 PAGE-Net instead of the compared saliency methods | PAGE-Net · ECCSD | F-score: 0.915 -> 0.924 | Helped |
| Use PAGE-Net instead of the compared saliency methods | PAGE-Net · DUT-OMRON | F-score: 0.758 -> 0.770 | Helped |
| Use PAGE-Net instead of the compared saliency methods | PAGE-Net · HKU-IS | MAE: 0.040 -> 0.037 | Helped |
| Use PAGE-Net instead of the compared saliency methods | PAGE-Net · PASCAL-S | F-score: 0.834 -> 0.835 | Helped |
| Use PAGE-Net instead of the compared saliency methods | PAGE-Net · SOD | F-score: 0.808 -> 0.796 | Hurt |
| Use PAGE-Net instead of the compared saliency methods | PAGE-Net · DUTS-TE | F-score: 0.807 -> 0.815 | Helped |
| Add CRF post-processing | PAGE-Net · ECCSD | MAE: 0.042 -> 0.035 | Helped |
| Add CRF post-processing | PAGE-Net · DUT-OMRON | F-score: 0.770 -> 0.770 | No clear effect |
| Add multi-scale pyramid attention (ablation) | PAGE-Net · ECCSD | MAE: 0.059 -> 0.042 | Helped |
| Add multi-scale pyramid attention (ablation) | PAGE-Net · DUT-OMRON | MAE: 0.080 -> 0.066 | Helped |
| Use multi-scale rather than single-scale attention (ablation) | PAGE-Net · ECCSD | MAE: 0.057 -> 0.042 | Helped |
| Add identity mapping to attention (ablation) | PAGE-Net · ECCSD | MAE: 0.051 -> 0.042 | Helped |
Closest papers by meaning
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.92)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.92)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.92)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.91)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.91)
- Exploring Salient Object Detection with Adder Neural Networks (AAAI 2025 · similarity 0.89)
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.