Research map / Detection and segmentation / CNN features
Deep Level Sets for 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 |
|---|---|---|---|
| train with the level set method instead of BCE loss (ablation) | VGG16-based saliency CNN · ECSSD | MAE: 0.104 -> 0.095 | Helped |
| add guided superpixel filtering (ablation) | CNN+LS · ECSSD | MAE: 0.095 -> 0.090 | Helped |
| include the level-set boundary-length term (ablation) | deep level set saliency CNN · PASCAL, ECSSD, OMRON, THUR | MAE | Helped |
| include the level-set compactness term (ablation) | deep level set saliency CNN · PASCAL, ECSSD, OMRON, THUR | MAE | Helped |
| increase guided-filter graph radius above 1 (ablation) | guided superpixel filtering layer · PASCAL, ECSSD, OMRON, THUR | MAE | Mixed |
| vary the approximate Heaviside support parameter ε (ablation) | deep level set network · PASCAL, ECSSD, OMRON, THUR | MAE | Mixed |
Closest papers by meaning
- Deep Contrast Learning for Salient Object Detection (CVPR 2016 · similarity 0.90)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.90)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.90)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.89)
- BASNet: Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.89)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · 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.