Research map / Detection and segmentation / CNN features
Disentangled High Quality Salient Object Detection
Lv Tang, Bo Li, Yijie Zhong, Shouhong Ding, Mofei Song
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 uncertainty loss to HRRN training (ablation) | HRRN · HRSOD-TE | BDE: 53.891 -> 48.468 | Improved |
| add uncertainty loss to HRRN training (ablation) | HRRN · DAVIS-S | BDE: 18.014 -> 15.676 | Improved |
| add high-resolution HRSOD training data to HRRN (ablation) | Ours · HRSOD-TE | F_beta^max: 0.918 -> 0.918 | No clear effect |
| add ME module to LRSCN (ablation) | LRSCN baseline · HRSOD-TE | F_beta^max: 0.900 -> 0.910 | Improved |
| add CF module to LRSCN (ablation) | LRSCN baseline · HRSOD-TE | F_beta^max: 0.900 -> 0.909 | Improved |
| combine ME and CF modules (ablation) | LRSCN baseline · HRSOD-TE | BDE: 65.732 -> 54.377 | Improved |
| add SGA module to LRSCN (ablation) | Baseline+MECF · HRSOD-TE | BDE: 54.377 -> 48.468 | Improved |
| replace CRF post-processing with HRRN (ablation) | Ours(LRSCN) · HRSOD-TE | BDE: 60.521 -> 48.468 | Improved |
| add HRRN refinement to EGNet (ablation) | EGNet · HRSOD-TE | F_beta^max: 0.883 -> 0.900 | Improved |
| add HRRN refinement to CPD (ablation) | CPD · HRSOD-TE | F_beta^max: 0.876 -> 0.891 | Improved |
| add HRRN refinement to BASNet (ablation) | BASNet · DAVIS-S | F_beta^max: 0.852 -> 0.875 | Improved |
| use HRRN instead of RRM refinement in BASNet (ablation) | BASNet · HRSOD-TE | F_beta^max: 0.878 -> 0.895 | Improved |
Closest papers by meaning
- Towards High-Resolution Salient Object Detection (ICCV 2019 · similarity 0.94)
- BASNet: Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.91)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.91)
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (TPAMI 2021 · similarity 0.90)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.90)
- ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection (ICML 2024 · similarity 0.90)
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.
