Research map / Detection and segmentation / CNN features
Pyramid Feature Attention Network for Saliency Detection
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 PFA instead of BDMPM | saliency detection · DUTS-test | wFβ: 0.8508 -> 0.8702 | Helped |
| use PFA instead of BDMPM | saliency detection · DUTS-test | MAE: 0.0484 -> 0.0405 | Helped |
| use PFA instead of BDMPM | saliency detection · ECSSD | wFβ: 0.9249 -> 0.9313 | Helped |
| use PFA instead of BDMPM | saliency detection · ECSSD | MAE: 0.0478 -> 0.0328 | Helped |
| use PFA instead of BDMPM | saliency detection · HKU-IS | wFβ: 0.9200 -> 0.9264 | Helped |
| use PFA instead of BDMPM | saliency detection · HKU-IS | MAE: 0.0392 -> 0.0324 | Helped |
| use PFA instead of BDMPM | saliency detection · PASCAL-S | wFβ: 0.8806 -> 0.8922 | Helped |
| use PFA instead of BDMPM | saliency detection · PASCAL-S | MAE: 0.0788 -> 0.0677 | Helped |
| use PFA instead of GRL | saliency detection · DUT-OMRON | wFβ: 0.7788 -> 0.8557 | Helped |
| use PFA instead of GRL | saliency detection · DUT-OMRON | MAE: 0.0632 -> 0.0414 | Helped |
| add CPFE to high-level features (ablation) | PFA · DUTS-test | MAE: 0.1003 -> 0.0815 | Helped |
| add channel-wise attention after CPFE (ablation) | PFA · DUTS-test | MAE: 0.0815 -> 0.0629 | Helped |
Closest papers by meaning
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.89)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.87)
- A Bi-Directional Message Passing Model for Salient Object Detection (CVPR 2018 · similarity 0.86)
- Deep Saliency With Encoded Low Level Distance Map and High Level Features (CVPR 2016 · similarity 0.86)
- Pyramid Grafting Network for One-Stage High Resolution Saliency Detection (CVPR 2022 · similarity 0.85)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · 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.