Research map / Detection and segmentation / CNN features
Salient Object Subitizing
Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian L. Price, Radomír Měch
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 two-stage pre-fine-tuning on synthetic images (ablation) | GoogleNet SOS CNN · SOS test set | mean AP: 78.6 -> 80.4 | Improved |
| add synthetic images by mixing with real data instead of pre-training (ablation) | GoogleNet SOS CNN · SOS test set | mean AP: 78.6 -> 77.8 | No clear effect |
| fine-tune the whole network instead of only the output layer (ablation) | GoogleNet · SOS test set | mean AP: 61.3 -> 78.6 | Improved |
| synthetic pre-training for 3-object images (ablation) | GoogleNet SOS CNN · SOS test set | AP for 3 objects: 58.6 -> 64.3 | Improved |
| synthetic pre-training for 0-object images (ablation) | GoogleNet SOS CNN · SOS test set | AP for 0 objects: 93.6 -> 93.5 | No clear effect |
| use CNN features instead of SIFT+IVF | GoogleNet without fine-tuning · SOS test set | mean AP: 50.1 -> 61.3 | Improved |
| add synthetic pre-training to AlexNet (ablation) | AlexNet SOS CNN · SOS test set | mean AP: 70.1 -> 71.6 | Improved |
| add synthetic pre-training to VGG16 (ablation) | VGG16 SOS CNN · SOS test set | mean AP: 77.5 -> 80.2 | Improved |
| add synthetic pre-training with only 25% real data (ablation) | GoogleNet SOS CNN · SOS test set (25% real data) | mean AP: 71.6 -> 76.3 | Improved |
| add synthetic pre-training with 50% real data (ablation) | GoogleNet SOS CNN · SOS test set (50% real data) | mean AP: 75.3 -> 78.2 | Improved |
| replace GoogleNet with AlexNet (ablation) | SOS CNN · SOS test set | mean AP: 78.6 -> 70.1 | Hurt |
| cue unconstrained salient object detection with predicted object count | USOD · MSO | F-score: 75.7 -> 79.5 | Improved |
Closest papers by meaning
- Delving Into Salient Object Subitizing and Detection (ICCV 2017 · similarity 0.91)
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 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 0.89)
- Relative Saliency and Ranking: Models, Metrics, Data and Benchmarks (TPAMI 2019 · similarity 0.88)
- Reverse Attention for Salient Object Detection (ECCV 2018 · similarity 0.88)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.88)
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.
