Research map / Detection and segmentation / CNN features
Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection
Nian Liu, Ni Zhang, Ling Shao, Junwei Han
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 mutual attention (MA) (ablation) | baseline RGB-D SOD · LFSD | maxF: 0.819 -> 0.864 | Improved |
| add mutual attention (MA) (ablation) | baseline RGB-D SOD · NJUD | S-measure: 0.883 -> 0.898 | Improved |
| add mutual attention (MA) (ablation) | baseline RGB-D SOD · ReDWeb-S | MAE: 0.109 -> 0.115 | Hurt |
| add contrast mechanism (MAC) (ablation) | MA model · NJUD | S-measure: 0.898 -> 0.901 | Improved |
| add non-local module (NL) (ablation) | MAC model · LFSD | S-measure: 0.862 -> 0.874 | Improved |
| add contrast mutual decoder (CMD) (ablation) | MAC+NL · LFSD | maxF: 0.868 -> 0.881 | Improved |
| add selective attention (SMAC+SCMD) (ablation) | MAC+NL+CMD · ReDWeb-S | MAE: 0.107 -> 0.098 | Improved |
| add selective attention (SMAC+SCMD) (ablation) | MAC+NL+CMD · LFSD | maxF: 0.881 -> 0.874 | Hurt |
| use mutual attention instead of self-attention (ablation) | baseline · LFSD | maxF: 0.796 -> 0.864 | Improved |
| use MAC+NL instead of S2MA (ablation) | SMAC · LFSD | S-measure: 0.862 -> 0.874 | Improved |
| use high-order SMAC fusion instead of concatenation fusion (ablation) | SMAC decoder · ReDWeb-S | S-measure: 0.781 -> 0.801 | Improved |
| use SMAC instead of summation fusion (ablation) | SMAC decoder · NJUD | S-measure: 0.899 -> 0.911 | Improved |
Closest papers by meaning
- Learning Selective Self-Mutual Attention for RGB-D Saliency Detection (CVPR 2020 · similarity 0.95)
- RGB-D Salient Object Detection with Cross-Modality Modulation and Selection (ECCV 2020 · similarity 0.93)
- CNN-Based RGB-D Salient Object Detection: Learn, Select, and Fuse (IJCV 2021 · similarity 0.92)
- Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion (CVPR 2021 · similarity 0.92)
- Siamese Network for RGB-D Salient Object Detection and Beyond (TPAMI 2021 · similarity 0.91)
- RGB-D Saliency Detection via Cascaded Mutual Information Minimization (ICCV 2021 · similarity 0.91)
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.
