Research map / Detection and segmentation / CNN features
Accurate RGB-D Salient Object Detection via Collaborative Learning
Wei Ji, Jingjing Li, Miao Zhang, Yongri Piao, Huchuan Lu
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 knowledge collector (triple-attention fusion of edge, saliency, depth knowledge) (ablation) | CoNet · NJUD and NLPR | MAE: 9.6% points | Improved |
| add global guidance module (ablation) | backbone network · NJUD and NLPR | saliency metrics | Improved |
| add edge supervision on low-level feature (ablation) | backbone with GGM · NJUD and NLPR | F-measure | Improved |
| add saliency supervision on low-level feature (ablation) | backbone with edge supervision · NJUD and NLPR | saliency metrics | Hurt |
| add saliency supervision on high-level feature (ablation) | backbone with edge supervision · NJUD and NLPR | saliency metrics | Improved |
| add depth supervision on high-level feature (ablation) | CoNet · NJUD and NLPR | saliency metrics | Improved |
| add mutual-benefit saliency attention and depth channel attention (ablation) | CoNet · NJUD and NLPR | saliency metrics | Improved |
| add edge and saliency attention (Att_edge, Att_sal) in knowledge collector (ablation) | CoNet · NJUD and NLPR | F-measure and MAE | Improved |
| add depth attention knowledge in knowledge collector (ablation) | CoNet · NJUD and NLPR | saliency metrics | Improved |
| use learned depth estimation instead of a depth network and depth input at inference | CoNet · Model complexity | FPS: enhances FPS by 55% | Improved |
Closest papers by meaning
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.93)
- Select, Supplement and Focus for RGB-D Saliency Detection (CVPR 2020 · similarity 0.92)
- A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection (CVPR 2020 · similarity 0.92)
- Siamese Network for RGB-D Salient Object Detection and Beyond (TPAMI 2021 · similarity 0.92)
- RGB-D Saliency Detection via Cascaded Mutual Information Minimization (ICCV 2021 · similarity 0.92)
- RGB-D Salient Object Detection with Cross-Modality Modulation and Selection (ECCV 2020 · 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.
