Research map / Detection and segmentation / CNN features
Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking
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 group exchange-masking (GEM) training to the baseline (ablation) | CoSOD model · CoSal2015 | Sα: 0.854 -> 0.883 | Helped |
| Add the latent variable generator branch (LVGB) to the baseline (ablation) | CoSOD model · CoSal2015 | Sα: 0.854 -> 0.877 | Helped |
| Add the CoSOD transformer branch (CoSOD-TB) to the baseline (ablation) | CoSOD model · CoSal2015 | MAE: 0.060 -> 0.053 | Helped |
| Add GEM to the CoSOD model (ablation) | GEM · CoSal2015 | Emaxφ: 0.887 -> 0.928 | Helped |
| Add LVGB to the CoSOD model (ablation) | LVGB · CoSal2015 | Fmaxβ: 0.860 -> 0.872 | Helped |
| Add CoSOD-TB to the CoSOD model (ablation) | CoSOD-TB · CoSal2015 | Sα: 0.854 -> 0.874 | Helped |
| Use the full GEM, LVGB, and CoSOD-TB design rather than the baseline (ablation) | CoSOD model · CoCA | Fmaxβ: 0.564 -> 0.599 | Helped |
| Use the full GEM method rather than DCFM | CoSOD model · CoSOD3k | Fmaxβ: 0.805 -> 0.829 | Helped |
| Use the full GEM method rather than DCFM | CoSOD model · CoCA | MAE: 0.085 -> 0.095 | Hurt |
| Use the full GEM method rather than DCFM | CoSOD model · CoCA | Fmaxβ: 0.598 -> 0.599 | Helped |
Closest papers by meaning
- CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection (CVPR 2024 · similarity 0.92)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.92)
- Taking a Deeper Look at Co-Salient Object Detection (CVPR 2020 · similarity 0.91)
- Visual Consensus Prompting for Co-Salient Object Detection (CVPR 2025 · similarity 0.89)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.87)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.84)
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.