Research map / Detection and segmentation / CNN features
Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion
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 DSA²F instead of ATSA | RGB-D SOD · DUT-RGBD | Fβ: .920 -> .926 | Helped |
| Use DSA²F instead of BBS-Net | RGB-D SOD · NJUD | Fβ: .899 -> .901 | Helped |
| Use DSA²F instead of CAS-GNN | RGB-D SOD · NLPR | Fβ: .888 -> .897 | Helped |
| Use DSA²F instead of CAS-GNN | RGB-D SOD · SSD | Fβ: .840 -> .852 | Helped |
| Use DSA²F instead of CoNet | RGB-D SOD · STEREO | Fβ: .885 -> .898 | Helped |
| Use DSA²F instead of CMWNet | RGB-D SOD · LFSD | Fβ: .870 -> .882 | Helped |
| Use DSA²F instead of UC-Net | RGB-D SOD · RGBD135 | Fβ: .905 -> .896 | Hurt |
| Add DSAM with element-wise multiplication (ablation) | baseline RGB-D model · DUT-RGBD | Fβ: .830 -> .889 | Helped |
| Use element-wise multiplication rather than summation or concatenation in DSAM (ablation) | DSAM · DUT-RGBD | Fβ: .875, .873 -> .889 | Helped |
| Add automatic multi-modal fusion after DSAM (ablation) | DSA²F · DUT-RGBD | Fβ: .889 -> .926 | Helped |
| Use 3 depth regions instead of 1, 2, 4, or 5 (ablation) | DSAM · DUT-RGBD | Fβ: .854, .874, .844, .831 -> .889 | Mixed |
| Add MM, MS, GA, and SR cells sequentially (ablation) | multi-modal fusion search space · DUT-RGBD | Fβ: .889 -> .908 -> .912 -> .918 -> .919 | Helped |
Closest papers by meaning
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.92)
- Calibrated RGB-D Salient Object Detection (CVPR 2021 · similarity 0.92)
- RGB-D Salient Object Detection via 3D Convolutional Neural Networks (AAAI 2021 · similarity 0.92)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.89)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.88)
- Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 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.