Research map / Detection and segmentation / Open-set and few-shot detection
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
Deng-Ping Fan, Ming-Ming Cheng, Jiang-Jiang Liu, Shang-Hua Gao, Qibin Hou, Ali Borji
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 |
|---|---|---|---|
| evaluate on big-object images instead of all salient images | DSS · SOC Big Object | S-measure: 28.9% loss | Hurt |
| evaluate on big-object images instead of all salient images | MC · SOC Big Object | S-measure: 20.8% loss | Hurt |
| evaluate on big-object images instead of all salient images | RFCN · SOC Big Object | S-measure: 23.8% loss | Hurt |
| evaluate on big-object images instead of all salient images | IMC · SOC Big Object | S-measure: 3.2% | Improved |
| evaluate on small-object images instead of all salient images | IMC · SOC Small Object | S-measure: 4.6% degradation | Hurt |
| evaluate on small-object images instead of all salient images | all SOD models · SOC Small Object | S-measure: from DSS -0.3% to LEGS -5.6% | Hurt |
| evaluate on heterogeneous-object images instead of all salient images | all SOD models · SOC Heterogeneous Object | S-measure: 3.9% to 9.7% | Improved |
| use multi-scale superpixel inputs without global semantics | MDF · SOC Big Object | S-measure: .610 -> .461 | Hurt |
| evaluate on occlusion images using multi-scale or uncertain features | DS, AMU, UCF · SOC Occlusion | S-measure: DS .719 -> .725; AMU .705 -> .725; UCF .678 -> .701 | Improved |
| train multi-task with weak supervision (WSS) versus fully supervised single-task | WSS · SOC test (all) | S-measure: .785 | No clear effect |
Closest papers by meaning
- Salient Objects in Clutter (TPAMI 2022 · similarity 0.97)
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (TPAMI 2021 · similarity 0.94)
- Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach (TPAMI 2025 · similarity 0.93)
- Breaking Barriers, Localizing Saliency: A Large-Scale Benchmark and Baseline for Condition-Constrained Salient Object Detection (TPAMI 2025 · similarity 0.93)
- Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes (ICCV 2025 · similarity 0.92)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (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.
