Research map / Detection and segmentation / CNN features
Deep Saliency With Encoded Low Level Distance Map and High Level Features
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 |
|---|---|---|---|
| combine ELD-map with VGG16 high-level features | saliency detection · PASCAL-S | F-measure: 0.737 -> 0.771 | Helped |
| combine ELD-map with VGG16 high-level features | saliency detection · ECSSD | F-measure: 0.837 -> 0.867 | Helped |
| combine ELD-map with VGG16 high-level features | saliency detection · DUT-OMRON | F-measure: 0.703 -> 0.719 | Helped |
| combine ELD-map with VGG16 high-level features | saliency detection · THUR15K | F-measure: 0.686 -> 0.731 | Helped |
| combine ELD-map with VGG16 high-level features | saliency detection · ASD | F-measure: 0.931 -> 0.924 | Hurt |
| add 1×1 convolutional encoding to low-level distances (ablation) | ELD-HF · ECSSD | F-measure: 0.835 -> 0.867 | Helped |
| add 1×1 convolutional encoding to low-level distances (ablation) | ELD-HF · PASCAL-S | F-measure: 0.735 -> 0.770 | Helped |
| add VGG16 high-level features (ablation) | ELD · ECSSD | F-measure: 0.790 -> 0.867 | Helped |
| add VGG16 high-level features (ablation) | ELD · PASCAL-S | F-measure: 0.682 -> 0.770 | Helped |
| add ELD-map to high-level features and location distance (ablation) | HF · ECSSD | F-measure: 0.768 -> 0.867 | Helped |
| add ELD-map to high-level features and location distance (ablation) | HF · PASCAL-S | F-measure: 0.693 -> 0.770 | Helped |
| remove histogram features (ablation) | ELD-HF · saliency detection | performance | Hurt |
Closest papers by meaning
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective (CVPR 2018 · similarity 0.91)
- Shallow and Deep Convolutional Networks for Saliency Prediction (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 0.89)
- Deep Level Sets for Salient Object Detection (CVPR 2017 · similarity 0.89)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · 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.