Research map / Vision-language and multimodal / Cross-modal learning
Frequency-Aligned Cross-Modal Learning with Top-K Wavelet Fusion and Dynamic Expert Routing for Enhanced Retinal Disease Diagnosis
Yuxin Lin, Haoran Li, Haoyu Cao, Yongting Hu, Qihao Xu, Chengliang Liu, Xiaoling Luo, Zhihao Wu, Yong Xu, Wei Wang
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 CMER (ablation) | CMER+TEWF · MMAD | F1: 0.901 -> 0.925 | Improved |
| add CMER (ablation) | CMER+TEWF · MMAD | Accuracy: 0.846 -> 0.881 | Improved |
| add wavelet transform before cross-attention (ablation) | CMER+TEWF · MMAD | F1: 0.914 -> 0.925 | Improved |
| add wavelet transform before cross-attention (ablation) | CMER+TEWF · MMAD | Accuracy: 0.874 -> 0.881 | Improved |
| add cross-attention instead of summing modalities (ablation) | CMER+TEWF · MMAD | F1: 0.907 -> 0.925 | Improved |
| add cross-attention instead of summing modalities (ablation) | CMER+TEWF · MMAD | Accuracy: 0.853 -> 0.881 | Improved |
| add both CMER and TEWF (ablation) | CMER+TEWF · MMAD | F1: 0.894 -> 0.925 | Improved |
| add both CMER and TEWF (ablation) | CMER+TEWF · MMAD | Accuracy: 0.832 -> 0.881 | Improved |
| use N=6 experts (K=2) in CMER (ablation) | CMER+TEWF · MMAD | F1: 92.5% | Improved |
| route K=2 experts rather than other K (ablation) | CMER+TEWF · MMAD | F1: 92.5% | Improved |
| full method vs MM-CNN da baseline | CMER+TEWF · MMAD | F1: 0.914 -> 0.925 | Improved |
| full method vs MM-CNN on GAMMA | CMER+TEWF · GAMMA | Kappa: 0.810 -> 0.841 | Improved |
Closest papers by meaning
- FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs (NeurIPS 2026 · similarity 0.85)
- Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading (AAAI 2025 · similarity 0.85)
- Multi-modal Vision Pre-training for Medical Image Analysis (CVPR 2025 · similarity 0.84)
- SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus Image (AAAI 2025 · similarity 0.83)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.83)
- VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception (NeurIPS 2024 · similarity 0.83)
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.
