Research map / Vision-language and multimodal / Cross-modal learning
Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion
Zengyi Yang, Yu Liu, Juan Cheng, Zhiqin Zhu, Yafei Zhang, Huafeng Li
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 |
|---|---|---|---|
| apply semantic compensation (RSC) to the frozen fusion network (ablation) | CLDyN · M3FD object detection (YOLOv5) | mAP50-95: 0.6076 -> 0.6304 | Improved |
| apply RSC compensation to a different detector without retraining (ablation) | CLDyN · M3FD detection (DETR) | mAP50-95: 0.5610 -> 0.5810 | Improved |
| add closed-loop optimization mechanism (vs Model I) (ablation) | CLDyN · M3FD object detection | mAP50-95: 0.6272 -> 0.6304 | Improved |
| add closed-loop optimization mechanism (vs Model I) (ablation) | CLDyN · VT5000 SOD | mFbeta: 0.8136 -> 0.8129 | No clear effect |
| add reward loss (vs Model II) (ablation) | CLDyN · M3FD object detection | mAP50-95: 0.6276 -> 0.6304 | Improved |
| replace plain conv networks with RSC (vs Model III) (ablation) | CLDyN · FMB segmentation | mIoU: 60.07 -> 60.34 | Improved |
| use CLDyN instead of joint-training fusion methods | CLDyN · multi-task (OD, Seg, SOD) | parameters: 0.46M vs 39.95M-134.97M | Improved |
| use CLDyN vs MRFS joint training on its trained task | CLDyN · FMB segmentation | mIoU: 61.48 -> 60.34 | Hurt |
| use CLDyN fusion quality vs prior methods | CLDyN · M3FD fusion | QAB/F: 0.6601 -> 0.6900 | Improved |
| use CLDyN fusion on VT5000 | CLDyN · VT5000 fusion | MI: 2.5749 -> 2.3352 | Hurt |
Closest papers by meaning
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.88)
- Task-Customized Mixture of Adapters for General Image Fusion (CVPR 2024 · similarity 0.86)
- Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion (ICML 2025 · similarity 0.85)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.85)
- Task-driven Image Fusion with Learnable Fusion Loss (CVPR 2025 · similarity 0.85)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.85)
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.
