Research map / Detection and segmentation / CNN features
Re-thinking Co-Salient Object Detection
Deng-Ping Fan, Tengpeng Li, Lin Liu Zheng, Ge-Peng Ji, Dingwen Zhang, Ming‐Ming Cheng, Huazhu Fu, Jianbing Shen
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 co-attention projection (ablation) | Amulet · CoSal2015 | max F-measure: .684 -> .758 | Improved |
| add co-attention projection (ablation) | PiCANet · CoSal2015 | max F-measure: .799 -> .818 | Improved |
| add co-attention projection (ablation) | EGNet · CoSal2015 | max F-measure: .786 -> .832 | Improved |
| add co-attention projection (ablation) | Amulet · CoSOD3k | max F-measure: .629 -> .700 | Improved |
| add co-attention projection (ablation) | PiCANet · CoSOD3k | MAE: .137 -> .095 | Improved |
| add co-attention projection (ablation) | EGNet · CoSOD3k | max F-measure: .702 -> .736 | Improved |
| add co-attention projection (ablation) | EGNet · CoSal2015 | S-measure: .818 -> .836 | Improved |
| add co-attention projection (ablation) | Amulet · CoSal2015 | S-measure: .719 -> .744 | Improved |
| add co-attention projection (ablation) | Amulet · iCoSeg | max E-measure: .877 -> .878 | No clear effect |
| add co-attention projection (ablation) | EGNet · iCoSeg | max F-measure: .875 -> .876 | No clear effect |
| add co-attention projection (ablation) | EGNet · iCoSeg | S-measure: .875 -> .875 | No clear effect |
| add co-attention projection (ablation) | PiCANet · CoSOD3k | S-measure: .750 -> .758 | Improved |
Closest papers by meaning
- Taking a Deeper Look at Co-Salient Object Detection (CVPR 2020 · similarity 0.98)
- Self-supervised co-salient object detection via feature correspondences at multiple scales (ECCV 2024 · similarity 0.94)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.94)
- Visual Consensus Prompting for Co-Salient Object Detection (CVPR 2025 · similarity 0.91)
- CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection (CVPR 2024 · similarity 0.91)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · 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.
