Random Token Fusion for Multi-View Medical Diagnosis
This addresses overfitting in multi-view medical image analysis for improved diagnostic models, though it appears incremental as an enhancement to existing fusion methods.
The paper tackles overfitting and trivial solutions in multi-view medical diagnosis by introducing Random Token Fusion (RTF), which integrates randomness into feature fusion during training to enhance robustness and accuracy without inference cost, validated on mammography and chest X-ray benchmarks.
In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on view-specific features, which can lead to trivial solutions. In this work, we introduce Random Token Fusion (RTF), a novel technique designed to enhance multi-view medical image analysis using vision transformers. By integrating randomness into the feature fusion process during training, RTF addresses the issue of overfitting and enhances the robustness and accuracy of diagnostic models without incurring any additional cost at inference. We validate our approach on standard mammography and chest X-ray benchmark datasets. Through extensive experiments, we demonstrate that RTF consistently improves the performance of existing fusion methods, paving the way for a new generation of multi-view medical foundation models.