Research map / Detection and segmentation / CNN features
Salient Object Detection Driven by Fixation Prediction
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 |
|---|---|---|---|
| use fixation prediction as a prior to guide salient-object segmentation (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.913 -> 0.928; 0.915 -> 0.920; 0.831 -> 0.857 | Helped |
| use convLSTM modules rather than convolution layers for saliency refinement (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.891 -> 0.928; 0.887 -> 0.920; 0.797 -> 0.857 | Helped |
| add progressively finer lower-layer features through the top-down hierarchy (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.853 -> 0.928; 0.830 -> 0.920; 0.739 -> 0.857 | Helped |
| add the precision-derived loss LP (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.923 -> 0.928; 0.917 -> 0.920; 0.852 -> 0.857 | Helped |
| add the recall-derived loss LR (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.924 -> 0.928; 0.915 -> 0.920; 0.854 -> 0.857 | Helped |
| add the F-measure-derived loss LF (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.924 -> 0.928; 0.916 -> 0.920; 0.854 -> 0.857 | Helped |
| add the MAE-derived loss LMAE (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.921 -> 0.928; 0.914 -> 0.920; 0.850 -> 0.857 | Helped |
| add the four extra metric-derived losses (ablation) | ASNet · ECCSD, HKU-IS, and PASCAL-S | F-measure: 0.917 -> 0.928; 0.912 -> 0.920; 0.847 -> 0.857 | Helped |
Closest papers by meaning
- Saliency Unified: A Deep Architecture for Simultaneous Eye Fixation Prediction and Salient Object Segmentation (CVPR 2016 · similarity 0.92)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.91)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.91)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.91)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.90)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · 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.