Research map / Detection and segmentation / CNN features
Co-Salient Object Detection with Co-Representation Purification
Ziyue Zhu, Zhao Zhang, Lin Liu Zheng, Xing Sun, Ming‐Ming Cheng
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 SOD head to baseline (ablation) | CoRP baseline · CoCA | S-measure: 0.560 -> 0.608 | Improved |
| add SOD head to baseline (ablation) | CoRP baseline · CoSal2015 | S-measure: 0.699 -> 0.800 | Improved |
| add PCS on top of SOD head (ablation) | CoRP · CoCA | S-measure: 0.608 -> 0.640 | Improved |
| add PCS on top of SOD head (ablation) | CoRP · CoSOD3k | S-measure: 0.753 -> 0.800 | Improved |
| add PCS on top of SOD head (ablation) | CoRP · CoSal2015 | S-measure: 0.800 -> 0.869 | Improved |
| use PCS instead of using the proxy directly as co-representation (ablation) | CoRP · CoCA | S-measure: 0.551 -> 0.640 | Improved |
| use PCS instead of using the proxy directly as co-representation (ablation) | CoRP · CoSOD3k | S-measure: 0.744 -> 0.800 | Improved |
| use proxy directly as co-representation instead of no proxy (ablation) | baseline + SOD · CoCA | S-measure: 0.608 -> 0.551 | Hurt |
| add RPP recurrent proxy purification (ablation) | CoRP · CoCA | S-measure: 0.640 -> 0.686 | Improved |
| add RPP recurrent proxy purification (ablation) | CoRP · CoSOD3k | S-measure: 0.800 -> 0.820 | Improved |
| increase iterations from T=1 to T=2 (ablation) | CoRP · CoCA | S-measure: 0.640 -> 0.672 | Improved |
| increase iterations from T=3 to T=6 (ablation) | CoRP · CoCA | S-measure: 0.686 -> 0.693 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- GCoNet — GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector (TPAMI 2023) · better on 3 of 3 shared results
- ICNet — ICNet: Intra-saliency Correlation Network for Co-Saliency Detection (NeurIPS 2020) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Re-thinking Co-Salient Object Detection (TPAMI 2021 · similarity 0.91)
- Self-supervised co-salient object detection via feature correspondences at multiple scales (ECCV 2024 · similarity 0.90)
- Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection (TPAMI 2025 · similarity 0.89)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.89)
- Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection (CVPR 2023 · similarity 0.89)
- CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection (CVPR 2024 · 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.
