Research map / Detection and segmentation / CNN features
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use CDDFuse instead of the strongest reported baseline | Infrared-visible image fusion · MSRS test | VIF: 0.77 -> 1.05 | Helped |
| Use CDDFuse instead of the strongest reported baseline | Infrared-visible image fusion · TNO | VIF: 0.60 -> 0.77 | Helped |
| Use CDDFuse instead of the strongest reported baseline | Infrared-visible image fusion · RoadScene | VIF: 0.63 -> 0.69 | Helped |
| Use CDDFuse fused images instead of the strongest reported baseline | YOLOv5 object detection · M³FD | mAP@0.5: 80.82 -> 81.13 | Helped |
| Use CDDFuse fused images instead of U2F fused images | DeeplabV3+ semantic segmentation · MSRS | mIOU: 61.7 -> 64.3 | Helped |
| Replace division with subtraction in the decomposition loss (ablation) | CDDFuse · MSRS test | VIF: 1.05 -> 0.98 | Hurt |
| Add the correlation-driven decomposition loss (ablation) | CDDFuse · MSRS test | VIF: 0.96 -> 1.05 | Helped |
| Use LT blocks rather than INN blocks in BTE (ablation) | CDDFuse · MSRS test | VIF: 1.00 -> 1.05 | Helped |
| Use INN rather than LT blocks in DCE (ablation) | CDDFuse · MSRS test | VIF: 1.00 -> 1.05 | Helped |
| Use INN rather than CNN blocks in DCE (ablation) | CDDFuse · MSRS test | VIF: 0.98 -> 1.05 | Helped |
| Use two-stage training rather than simultaneous training (ablation) | CDDFuse · MSRS test | VIF: 0.97 -> 1.05 | Helped |
Closest papers by meaning
- When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion (NeurIPS 2026 · similarity 0.87)
- SMR-Net: Semantic-Guided Mutually Reinforcing Network for Cross-Modal Image Fusion and Salient Object Detection (AAAI 2025 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.84)
- Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion (NeurIPS 2026 · similarity 0.84)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.84)
- Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model (NeurIPS 2024 · similarity 0.84)
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.