Research map / Detection and segmentation / CNN features
Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection
Hao Tang, Zechao Li, Dong Zhang, Shengfeng He, Jinhui Tang
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 the full modality-induced feature modulator (MFM) (ablation) | single-flow baseline · VT5000 | S-measure: 0.876 -> 0.884 | Improved |
| add CFE to MFM that has only AFF (ablation) | MFM · VT5000 | S-measure: 0.881 -> 0.884 | Improved |
| add AFF to MFM that has only CFE (ablation) | MFM · VT5000 | S-measure: 0.883 -> 0.884 | Improved |
| add a second flow (flow x2) (ablation) | baseline with MFM · VT5000 | S-measure: 0.884 -> 0.890 | Improved |
| add RASPM (ablation) | triple-flow decoders · VT821 | S-measure: 0.883 -> 0.885 | Improved |
| add MDAM (ablation) | flow x2 + RASPM · VT5000 | S-measure: 0.889 -> 0.894 | Improved |
| add DW to MDAM (ablation) | MDAM · VT5000 | S-measure: 0.892 -> 0.894 | Improved |
| add DoE to MDAM (ablation) | MDAM · VT5000 | S-measure: 0.893 -> 0.894 | Improved |
| use RASPM instead of ASPP (ablation) | decoder module · VT5000 | S-measure: 0.889 -> 0.894 | Improved |
| add atrous convolution to RASPM (ablation) | RASPM · VT5000 | S-measure: 0.893 -> 0.894 | Improved |
| add weighted IoU loss to weighted BCE loss (ablation) | ConTriNet · VT5000 | F-measure: 0.840 -> 0.863 | Improved |
| add weighted BCE loss to weighted IoU loss (ablation) | ConTriNet · VT5000 | F-measure: 0.857 -> 0.863 | Improved |
Closest papers by meaning
- RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation (ECCV 2026 · similarity 0.91)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.90)
- A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection (ECCV 2020 · similarity 0.90)
- Siamese Network for RGB-D Salient Object Detection and Beyond (TPAMI 2021 · similarity 0.90)
- Specificity-Preserving RGB-D Saliency Detection (ICCV 2021 · similarity 0.90)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.89)
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.
