Research map / Detection and segmentation / CNN features
Uncertainty-Aware Joint Salient Object and Camouflaged 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 |
|---|---|---|---|
| Use selected easy COD training samples as hard SOD samples (ablation) | SOD model · DUTS | S-measure: .885 -> .891 | Helped |
| Jointly train SOD and COD instead of training SOD separately (ablation) | SOD model · DUTS | S-measure: .891 -> .894 | Helped |
| Add the similarity measure to joint SOD/COD training (ablation) | SOD model · DUTS | S-measure: .894 -> .893 | Hurt |
| Add adversarial learning to joint SOD/COD training (ablation) | SOD model · DUTS | S-measure: .893 -> .891 | Hurt |
| Jointly train SOD and COD instead of training COD separately (ablation) | COD model · CAMO | S-measure: 0.792 -> 0.797 | Helped |
| Add the similarity measure to joint SOD/COD training (ablation) | COD model · CAMO | S-measure: 0.797 -> 0.799 | Helped |
| Add adversarial learning to joint SOD/COD training (ablation) | COD model · CAMO | S-measure: 0.799 -> 0.793 | Hurt |
| Use the joint uncertainty-aware method rather than the strongest listed baseline | SOD model · SOC | S-measure: .858 -> .845 | Hurt |
| Use the joint uncertainty-aware method rather than the strongest listed baseline | COD model · COD10K | S-measure: 0.776 -> 0.817 | Helped |
Closest papers by meaning
- Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning (AAAI 2022 · similarity 0.89)
- Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection (CVPR 2022 · similarity 0.88)
- Modeling the Distributional Uncertainty for Salient Object Detection Models (CVPR 2023 · similarity 0.88)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.88)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.86)
- Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection (ICML 2024 · similarity 0.86)
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.