Research map / Detection and segmentation / CNN features
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
Jing Zhang, Deng-Ping Fan, Yuchao Dai, Xin Yu, Yiran Zhong, Nick Barnes, Ling Shao
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 information minimization regularizer (lambda 0 -> 0.1) (ablation) | CMINet · NJU2K | S-measure: .918 -> .939 | Improved |
| add cascaded MI regularizer framework over the plain baseline (ablation) | CMINet · NJU2K | S-measure: .910 -> .939 | Improved |
| add MI regularizer: feature embedding cosine similarity (NLPR) (ablation) | CMINet · NLPR | cosine similarity of z_a, z_g: 0.90 -> 0.11 | Improved |
| use embedding dimension K=6 instead of K=3 (ablation) | CMINet · NJU2K | S-measure: .928 -> .939 | Improved |
| use embedding dimension K=6 instead of K=32 (ablation) | CMINet · NJU2K | S-measure: .924 -> .939 | Improved |
| use conv plus fc embedding instead of two fc layers (ablation) | CMINet · NJU2K | S-measure: .926 -> .939 | Improved |
| use regularizer weight 0.1 instead of 1 (ablation) | CMINet · NJU2K | S-measure: .919 -> .939 | Improved |
| add final fusion of P_a, P_g, P_f into P (ablation) | CMINet · NJU2K | S-measure: .925 -> .939 | Improved |
| add depth input (RGB-only to early-fusion RGB-D) (ablation) | CMINet encoder-decoder · NJU2K | S-measure: .898 -> .915 | Improved |
| polygon instead of scribble annotation supervision | CMINet weak baseline · COME15K-Normal | S-measure: .802 -> .827 | Improved |
Closest papers by meaning
- Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion (CVPR 2021 · similarity 0.92)
- Select, Supplement and Focus for RGB-D Saliency Detection (CVPR 2020 · similarity 0.92)
- Accurate RGB-D Salient Object Detection via Collaborative Learning (ECCV 2020 · similarity 0.92)
- Learning Selective Self-Mutual Attention for RGB-D Saliency Detection (CVPR 2020 · similarity 0.91)
- RGB-D Salient Object Detection with Cross-Modality Modulation and Selection (ECCV 2020 · similarity 0.91)
- Uncertainty Inspired RGB-D Saliency Detection (TPAMI 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.
