Research map / Detection and segmentation / CNN features
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
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 rank-aware refinement units and multi-stage saliency-map fusion (ablation) | RSDNet on PASCAL-S · PASCAL-S | SOR: 0.825 -> 0.852 | Helped |
| add rank-aware refinement units and multi-stage saliency-map fusion (ablation) | RSDNet on PASCAL-S · PASCAL-S | max-Fm: 0.873 -> 0.880 | Helped |
| add rank-aware refinement units and multi-stage saliency-map fusion (ablation) | RSDNet on PASCAL-S · PASCAL-S | AUC: 0.972 -> 0.971 | Hurt |
| add rank-aware refinement units and multi-stage saliency-map fusion (ablation) | RSDNet on PASCAL-S · PASCAL-S | avg-Fm: 0.834 -> 0.837 | Helped |
| scale ground-truth by a factor of 1000 (ablation) | RSDNet on PASCAL-S · PASCAL-S | max-Fm: 0.873 -> 0.874 | Helped |
| scale ground-truth by a factor of 1000 (ablation) | RSDNet on PASCAL-S · PASCAL-S | avg-Fm: 0.834 -> 0.796 | Hurt |
| add atrous pyramid pooling (ablation) | RSDNet on PASCAL-S · PASCAL-S | max-Fm: 0.873 -> 0.877 | Helped |
| add atrous pyramid pooling (ablation) | RSDNet on PASCAL-S · PASCAL-S | AUC: 0.972 -> 0.969 | Hurt |
| add atrous pyramid pooling and ground-truth scaling (ablation) | RSDNet on PASCAL-S · PASCAL-S | SOR: 0.825 -> 0.848 | Helped |
| use salient-object detection and ranking features for subitizing | RSDNet on SOS · SOS | overall AP: 0.79 -> 0.83 | Helped |
Closest papers by meaning
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.91)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · 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 0.91)
- What Is and What Is Not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors (CVPR 2017 · similarity 0.91)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (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.