[CVPR 2025] Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering

AMiF Paper URL

Pretrain

please look at pretrain.py

VQA Finetune

please look at VQA.py

Configuration of Model

please look at config directory

Reference

@inproceedings{zou2025alignment,
  title={Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering},
  author={Zou, Yuanhao and Yin, Zhaozheng},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={29623--29633},
  year={2025}
}