Multi-view classification problems are common in medical image analysis, forensics, and other domains where problem queries involve multi-image input. Existing multi-view classification methods are often tailored to a specific task. In this work, we repurpose off-the-shelf Hybrid CNN-Transformer networks for multi-view classification with either structured or unstructured views. Our approach incorporates a novel fusion scheme, mutual distillation, and minimal additional parameters. We demonstrate the effectiveness and generalization capability of our approach, MV-HFMD, on multiple multi-view classification tasks and show that it outperforms other multi-view approaches, even task-specific methods.

    @inproceedings{black2024multi,
    title={Multi-view Classification Using Hybrid Fusion and Mutual Distillation},
    author={Black, Samuel and Souvenir, Richard},
    booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
    pages={270--280},
    year={2024}
    }