Research map / Detection and segmentation / CNN features
DHSNet: Deep Hierarchical Saliency Network 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 |
|---|---|---|---|
| Add hierarchical refinement stages from RCL4 through RCL1 (ablation) | DHSNet · ECSSD | F-measure: 0.7941 -> 0.8645 | Helped |
| Replace GV-CNN with FCN for the coarse prediction (ablation) | DHSNet · ECSSD | F-measure: 0.8645 -> 0.8516 | Hurt |
| Use GV-CNN instead of FCN for the coarse prediction (ablation) | DHSNet · ECSSD | F-measure: 0.8516 -> 0.8645 | Helped |
| Replace RCLs with traditional convolutional layers (ablation) | DHSNet · ECSSD | F-measure: 0.8645 -> 0.8516 | Hurt |
| Use RCLs instead of traditional convolutional layers (ablation) | DHSNet · ECSSD | F-measure: 0.8516 -> 0.8645 | Helped |
| Use DHSNet rather than DeconvNet | salient object detection · ECSSD | F-measure: 0.8396 -> 0.8645 | Helped |
| Use DHSNet for inference | salient object detection · Runtime | runtime (s): 0.04* | Helped |
Closest papers by meaning
- 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)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.89)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.89)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.89)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 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.