Research map / Vision-language and multimodal / Cross-modal learning
Multi-Modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion
Bing Cao, Yiming Sun, Pengfei Zhu, Qinghua Hu
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 Mixture of Local Experts (MoLE) (ablation) | MoE-Fusion · M3FD | VIF: 0.8100 -> 1.0034 | Improved |
| add Mixture of Global Experts (MoGE) instead of a common decoder (ablation) | MoE-Fusion · M3FD | VIF: 0.8261 -> 1.0034 | Improved |
| use dynamic MoLE instead of attention-based local features (Att-Local) (ablation) | MoE-Fusion · M3FD | MI: 2.7320 -> 4.1949 | Improved |
| use fused images from MoE-Fusion for downstream detection | Faster R-CNN on FLIR · FLIR detection | mAP: 48.40 -> 55.80 | Improved |
| increase number of experts beyond 4 (E6K2, E8K2 vs E4K2) (ablation) | MoE-Fusion · FLIR | fusion metrics | No clear effect |
| select top-2 experts instead of 1, 3 or 4 (ablation) | MoE-Fusion · FLIR | fusion metrics | Improved |
| set alpha above 10 instead of 10 (ablation) | MoE-Fusion · FLIR | fusion metrics | Mixed |
| set alpha below 10 instead of 10 (ablation) | MoE-Fusion · FLIR | fusion metrics | Hurt |
Closest papers by meaning
- LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables (ICCV 2025 · similarity 0.86)
- More Than Meets the Eye: A Unified Image Fusion Framework via Semantic-Pixel Entropy Trade-off for Zero-Shot Generalization (CVPR 2026 · similarity 0.85)
- Test-Time Dynamic Image Fusion (NeurIPS 2024 · similarity 0.85)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · similarity 0.85)
- Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning (CVPR 2024 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · 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.
