Research map / Detection and segmentation / CNN features
Deep Embedding Features for Salient Object Detection
Read the paperCheck 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 |
|---|---|---|---|
| add Feature Embedding Network (FEN) to baseline (ablation) | DEF saliency network · ECSSD | F-measure: 0.821 -> 0.874 | Helped |
| add FEN to baseline (ablation) | DEF saliency network · DUTS-TE | F-measure: 0.721 -> 0.763 | Helped |
| add FEN to baseline (ablation) | DEF saliency network · ECSSD | MAE: 0.055 -> 0.046 | Helped |
| add recursive feature integration (RFIN stage-4) over FEN (ablation) | DEF saliency network · ECSSD | F-measure: 0.874 -> 0.905 | Helped |
| add recursive feature integration (RFIN stage-4) over FEN (ablation) | DEF saliency network · DUTS-TE | F-measure: 0.763 -> 0.813 | Helped |
| add recursive feature integration (RFIN stage-4) over FEN (ablation) | DEF saliency network · DUTS-TE | MAE: 0.067 -> 0.046 | Helped |
| add Guided Filter Refinement Network (GFRN) (ablation) | DEF saliency network · ECSSD | F-measure: 0.905 -> 0.915 | Helped |
| add GFRN (ablation) | DEF saliency network · DUTS-TE | F-measure: 0.813 -> 0.821 | Helped |
| add GFRN (ablation) | DEF saliency network · ECSSD | MAE: 0.037 -> 0.036 | Helped |
| use ResNet-101 instead of VGG-16 backbone (ablation) | DEF saliency network · ECSSD | F-measure: 0.889 -> 0.915 | Helped |
| use ResNet-101 instead of DenseNet-161 backbone (ablation) | DEF saliency network · DUTS-TE | F-measure: 0.792 -> 0.821 | Helped |
Closest papers by meaning
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.93)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.93)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.92)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.91)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.91)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.91)
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.