Research map / Detection and segmentation / CNN features
Select, Supplement and Focus for RGB-D Saliency 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 the proposed RGB-D framework with CIM and compensation-aware loss | RGB-D saliency detection · NJUD | MAE: 15.6% | Helped |
| add cross-modal attention unit (CAU) (ablation) | VGG-16 baseline · DUT-RGBD | S-measure: .869 -> .894 | Helped |
| add cross-modal attention unit (CAU) (ablation) | VGG-16 baseline · LFSD | S-measure: .775 -> .824 | Helped |
| add cross-modal attention unit (CAU) (ablation) | VGG-16 baseline · STEREO | S-measure: .791 -> .867 | Helped |
| add boundary supplement unit (BSU) (ablation) | VGG-16 baseline · DUT-RGBD | S-measure: .869 -> .900 | Helped |
| add boundary supplement unit (BSU) (ablation) | VGG-16 baseline · LFSD | S-measure: .775 -> .823 | Helped |
| add boundary supplement unit (BSU) (ablation) | VGG-16 baseline · STEREO | S-measure: .791 -> .869 | Helped |
| add compensation-aware loss to Baseline+CAU+BSU (ablation) | VGG-16 baseline with CAU and BSU · DUT-RGBD | S-measure: .904 -> .915 | Helped |
| add compensation-aware loss to Baseline+CAU+BSU (ablation) | VGG-16 baseline with CAU and BSU · LFSD | S-measure: .845 -> .859 | Helped |
| add compensation-aware loss to Baseline+CAU+BSU (ablation) | VGG-16 baseline with CAU and BSU · STEREO | S-measure: .883 -> .893 | Helped |
| set binary-mask count m to 2 rather than 10 (ablation) | CAU · DUT-RGBD | S-measure: .915 -> .898 | Hurt |
| set binary-mask count m to 5 rather than 10 (ablation) | CAU · DUT-RGBD | S-measure: .915 -> .911 | Hurt |
Closest papers by meaning
- Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion (CVPR 2021 · similarity 0.91)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.91)
- Learning Selective Self-Mutual Attention for RGB-D Saliency Detection (CVPR 2020 · similarity 0.90)
- A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection (CVPR 2020 · similarity 0.90)
- Calibrated RGB-D Salient Object Detection (CVPR 2021 · similarity 0.90)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · 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.