Research map / Detection and segmentation / CNN features
A Simple Pooling-Based Design for Real-Time 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 PPM and GGFs to FPN (ablation) | VGG-16 FPN · DUT-O | MaxF: 0.770 -> 0.790 | Helped |
| Add PPM and GGFs to FPN (ablation) | VGG-16 FPN · SOD | MaxF: 0.838 -> 0.855 | Helped |
| Add FAMs to FPN (ablation) | VGG-16 FPN · DUT-O | MaxF: 0.770 -> 0.798 | Helped |
| Add FAMs to FPN (ablation) | VGG-16 FPN · SOD | MaxF: 0.838 -> 0.852 | Helped |
| Add PPM to the GGM without GGFs (ablation) | VGG-16 FPN · DUT-O | MaxF: 0.790 -> 0.783 | Hurt |
| Add PPM to the GGM without GGFs (ablation) | VGG-16 FPN · SOD | MaxF: 0.855 -> 0.847 | Hurt |
| Add GGFs to the GGM without PPM (ablation) | VGG-16 FPN · DUT-O | MaxF: 0.790 -> 0.772 | Hurt |
| Add GGFs to the GGM without PPM (ablation) | VGG-16 FPN · SOD | MaxF: 0.855 -> 0.843 | Hurt |
| Jointly train using salient-object boundaries as edge supervision (ablation) | PoolNet with edge branch · PASCAL-S | MaxF: 0.838 -> 0.835 | Hurt |
| Jointly train using salient-object boundaries as edge supervision (ablation) | PoolNet with edge branch · DUT-O | MaxF: 0.806 -> 0.805 | Hurt |
| Jointly train using salient-object boundaries as edge supervision (ablation) | PoolNet with edge branch · SOD | MaxF: 0.861 -> 0.863 | Helped |
| Jointly train with standard edge datasets (ablation) | PoolNet with edge branch · PASCAL-S | MaxF: 0.838 -> 0.849 | Helped |
Closest papers by meaning
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.89)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.89)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.89)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.89)
- Exploring Salient Object Detection with Adder Neural Networks (AAAI 2025 · similarity 0.87)
- Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 2025 · similarity 0.87)
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.