Research map / Detection and segmentation / CNN features
Cross-Modal Weighting Network for RGB-D Salient Object Detection
Gongyang Li, Zhi Liu, Linwei Ye, Yang Wang, Haibin Ling
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 |
|---|---|---|---|
| enhance RGB features with depth (DeR) instead of depth with RGB (ReD) (ablation) | CMWNet · NJU2K-T | MAE: 0.056 -> 0.046 | Improved |
| enhance RGB features with depth (DeR) instead of depth with RGB (ReD) (ablation) | CMWNet · SSD | MAE: 0.063 -> 0.051 | Improved |
| add the depth map input (DW) (ablation) | CMWNet · NJU2K-T | MAE: 0.056 -> 0.046 | Improved |
| add CMW-L and CMW-M modules (ablation) | CMWNet · SSD | S-measure: 0.849 -> 0.875 | Improved |
| add CMW-L and CMW-M modules (ablation) | CMWNet · NJU2K-T | S-measure: 0.891 -> 0.903 | Improved |
| add CMW-H module (ablation) | CMWNet · SSD | max F-measure: 0.845 -> 0.871 | Improved |
| add CMW-H module (ablation) | CMWNet · NJU2K-T | max F-measure: 0.894 -> 0.902 | Improved |
| add RGB-to-RGB weighting (RW) (ablation) | CMWNet · SSD | S-measure: .868 -> .875 | Improved |
| use weighting instead of concatenating depth and RGB features (ablation) | CMWNet · SSD | max F-measure: .839 -> .871 | Improved |
| add global filter to DW (ablation) | CMWNet · SSD | MAE: .054 -> .051 | Improved |
| add global filter to RW (ablation) | CMWNet · SSD | S-measure: .875 -> .870 | Hurt |
| use cross-scale DW instead of same-scale in CMW-L&M (ablation) | CMWNet · SSD | MAE: .060 -> .051 | Improved |
Closest papers by meaning
- RGB-D Salient Object Detection with Cross-Modality Modulation and Selection (ECCV 2020 · similarity 0.90)
- CNN-Based RGB-D Salient Object Detection: Learn, Select, and Fuse (IJCV 2021 · similarity 0.89)
- Self-Supervised Pretraining for RGB-D Salient Object Detection (AAAI 2022 · similarity 0.89)
- Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (CVPR 2018 · similarity 0.88)
- A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection (ECCV 2020 · similarity 0.88)
- 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.
