Research map / Detection and segmentation / CNN features
Specificity-Preserving RGB-D Saliency Detection
Tao Zhou, Huazhu Fu, Geng Chen, Yi Zhou, Deng-Ping Fan, 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 CIM instead of simple concatenation fusion (ablation) | SP-Net · NJU2K | S-measure: .916 -> .925 | Improved |
| add cross-modal feature enhancement part of CIM on top of adaptive fusion (ablation) | SP-Net · NJU2K | S-measure: .919 -> .925 | Improved |
| add adaptive feature fusion part of CIM on top of cross-modal enhancement (ablation) | SP-Net · NJU2K | S-measure: .921 -> .925 | Improved |
| add cross-level propagation of CIM output to the next layer (ablation) | SP-Net · NJU2K | S-measure: .924 -> .925 | Improved |
| add the MFA module integrating modality-specific decoder features (ablation) | SP-Net · NJU2K | S-measure: .918 -> .925 | Improved |
| use MFA instead of cross-modal feature enhancement fusion (ablation) | SP-Net · NJU2K | S-measure: .924 -> .925 | Improved |
| use MFA instead of simple concatenation fusion (ablation) | SP-Net · NJU2K | S-measure: .921 -> .925 | Improved |
| add the two modality-specific decoders (ablation) | SP-Net · NJU2K | S-measure: .913 -> .925 | Improved |
| use shared decoder output instead of combining the two modality-specific decoders (ablation) | SP-Net · NJU2K | S-measure: .916 -> .925 | Improved |
| use five CIMs instead of one CIM (last layer only) (ablation) | SP-Net · NJU2K | S-measure: .918 -> .925 | Improved |
| use five CIMs instead of three CIMs (ablation) | SP-Net · NJU2K | S-measure: .920 -> .925 | Improved |
| use Res2Net-50 backbone instead of ResNet-50 (ablation) | SP-Net · NJU2K | S-measure: .922 -> .925 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- JL-DCF — JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (CVPR 2020) · better on 0 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RGB-D Salient Object Detection with Cross-Modality Modulation and Selection (ECCV 2020 · similarity 0.93)
- Self-Supervised Pretraining for RGB-D Salient Object Detection (AAAI 2022 · similarity 0.92)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.92)
- Siamese Network for RGB-D Salient Object Detection and Beyond (TPAMI 2021 · similarity 0.92)
- CNN-Based RGB-D Salient Object Detection: Learn, Select, and Fuse (IJCV 2021 · similarity 0.91)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · 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.
