Research map / Detection and segmentation / CNN features
BASNet: 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 BASNet instead of PiCANetR | salient object detection · ECSSD | maxFβ: 0.935 -> 0.942 | Helped |
| Use BASNet instead of PiCANetR | salient object detection · SOD | maxFβ: 0.856 -> 0.851 | Hurt |
| Use BASNet instead of PiCANetR | salient object detection · DUT-OMRON | maxFβ: 0.803 -> 0.805 | Helped |
| Use BASNet instead of PiCANetR | salient object detection · PASCAL-S | maxFβ: 0.857 -> 0.854 | Hurt |
| Use BASNet instead of PiCANetR | salient object detection · HKU-IS | maxFβ: 0.918 -> 0.928 | Helped |
| Use BASNet instead of PiCANetR | salient object detection · DUTS-TE | maxFβ: 0.860 -> 0.860 | No clear effect |
| Add the encoder-decoder architecture rather than baseline U-Net (ablation) | BASNet · ECSSD | maxFβ: 0.896 -> 0.929 | Helped |
| Add side-output supervision (ablation) | BASNet encoder-decoder · ECSSD | maxFβ: 0.929 -> 0.934 | Helped |
| Add RRM LC refinement (ablation) | BASNet encoder-decoder with side supervision · ECSSD | maxFβ: 0.934 -> 0.936 | Helped |
| Replace RRM LC with RRM MS refinement (ablation) | BASNet encoder-decoder with side supervision · ECSSD | maxFβ: 0.936 -> 0.935 | Hurt |
| Use the proposed RRM rather than RRM LC (ablation) | BASNet encoder-decoder with side supervision · ECSSD | maxFβ: 0.936 -> 0.937 | Helped |
| Use the combined BCE+SSIM+IoU loss rather than BCE alone (ablation) | BASNet · ECSSD | relaxF b β: 0.806 -> 0.826 | Helped |
Closest papers by meaning
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.91)
- Attentive Feedback Network for Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.91)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.91)
- Detect Globally, Refine Locally: A Novel Approach to Saliency Detection (CVPR 2018 · similarity 0.91)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.91)
- F³Net: Fusion, Feedback and Focus for Salient Object Detection (AAAI 2020 · similarity 0.90)
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.