Research map / Detection and segmentation / CNN features
Attentive Feedback Network for Boundary-Aware Salient Object 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 AFNet instead of PiCANet | salient object detection · DUTS-test | Fmaxβ: .851 -> .862 | Helped |
| Use AFNet instead of the strongest listed baseline | salient object detection · ECSSD | Fmaxβ: .931 -> .935 | Helped |
| Use AFNet instead of PiCANet | salient object detection · PASCAL-S | Fmaxβ: .868 -> .868 | No clear effect |
| Use AFNet instead of PiCANet | salient object detection · DUT-OMRON | Fmaxβ: .794 -> .797 | Helped |
| Use AFNet instead of PiCANet | salient object detection · HKU-IS | Fmaxβ: .921 -> .923 | Helped |
| Add ternary-attention feedback through AFMs (ablation) | AFNet · DUTS-test | Fmaxβ: .8586 -> .8624 | Helped |
| Add Boundary-Enhanced Loss (ablation) | AFNet · DUTS-test | Fmaxβ: .8557 -> .8624 | Helped |
| Use multi-scale GPMs rather than a single global module (ablation) | AFNet global saliency prediction · DUTS-test | Fmaxβ: .787 -> .791 | Helped |
| Replace fully-connected global prediction with GPM (ablation) | AFNet global saliency prediction · DUTS-test | Fmaxβ: .769 -> .791 | Helped |
| Replace dilated convolution global prediction with GPM (ablation) | AFNet global saliency prediction · DUTS-test | Fmaxβ: .779 -> .791 | Helped |
| Replace pyramid pooling global prediction with GPM (ablation) | AFNet global saliency prediction · DUTS-test | Fmaxβ: .781 -> .791 | Helped |
Closest papers by meaning
- BASNet: Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.91)
- F³Net: Fusion, Feedback and Focus for Salient Object Detection (AAAI 2020 · similarity 0.88)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.88)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.88)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.87)
- Geometry-Aware 3D Salient Object Detection Network (AAAI 2025 · 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.