Research map / Detection and segmentation / CNN features
Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection
Yi Wang, Ruili Wang, Xin Fan, Tianzhu Wang, Xiangjian He
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 |
|---|---|---|---|
| Use four enhancement iterations instead of one (ablation) | MENet · OMRON, DUTS-TE, HKU-IS, PASCAL-S, ECSSD, SOD | MAE: 0.0617 -> 0.0450; 0.0496 -> 0.0281; 0.0504 -> 0.0234; 0.0868 -> 0.0535; 0.0673 -> 0.0307; 0.1449 -> 0.0874 | Improved |
| Use four enhancement iterations instead of three (ablation) | MENet · OMRON, DUTS-TE, HKU-IS, PASCAL-S, ECSSD, SOD | MAE: 0.0504 -> 0.0450; 0.0389 -> 0.0281; 0.0383 -> 0.0234; 0.0685 -> 0.0535; 0.0503 -> 0.0307; 0.1147 -> 0.0874 | Improved |
| Add object-level loss to pixel- and region-level losses (ablation) | MENet · OMRON, DUTS-TE, HKU-IS, PASCAL-S, ECSSD | MAE: 0.0470 -> 0.0450; 0.0295 -> 0.0281; 0.0250 -> 0.0234; 0.0557 -> 0.0535; 0.0305 -> 0.0307 | Improved |
| Add object-level loss to pixel- and region-level losses (ablation) | MENet · SOD | MAE: 0.0886 -> 0.0874 | Improved |
| Use four sub-regions instead of one in region-level loss (ablation) | MENet · OMRON, DUTS-TE, HKU-IS, PASCAL-S, ECSSD, SOD | MAE: 0.0472 -> 0.0450; 0.0295 -> 0.0281; 0.0255 -> 0.0234; 0.0576 -> 0.0535; 0.0326 -> 0.0307; 0.0944 -> 0.0874 | Improved |
| Add gradient supervision to the multilevel hybrid loss (ablation) | MENet · OMRON, DUTS-TE, HKU-IS, PASCAL-S | MAE: 0.0470 -> 0.0450; 0.0295 -> 0.0281; 0.0250 -> 0.0234; 0.0557 -> 0.0535 | Improved |
| Add gradient supervision to the multilevel hybrid loss (ablation) | MENet · ECSSD | MAE: 0.0305 -> 0.0307 | Hurt |
| Add gradient supervision to the multilevel hybrid loss (ablation) | MENet · SOD | MAE: 0.0886 -> 0.0874 | Improved |
| Combine region-level loss with pixel-level loss (ablation) | MENet · OMRON, DUTS-TE, PASCAL-S, ECSSD, SOD | MAE: 0.0518 -> 0.0492; 0.0308 -> 0.0295; 0.0572 -> 0.0565; 0.0308 -> 0.0297; 0.0910 -> 0.0841 | Improved |
| Combine region-level loss with pixel-level loss (ablation) | MENet · HKU-IS | MAE: 0.0237 -> 0.0252 | Hurt |
Closest papers by meaning
- Disentangled High Quality Salient Object Detection (ICCV 2021 · similarity 0.89)
- DVSOD: RGB-D Video Salient Object Detection (NeurIPS 2023 · similarity 0.89)
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (TPAMI 2021 · similarity 0.89)
- Salient Objects in Clutter (TPAMI 2022 · similarity 0.89)
- Specificity-Preserving RGB-D Saliency Detection (ICCV 2021 · similarity 0.89)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.87)
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.
