Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models
This addresses generalization challenges in medical imaging for healthcare applications, but it is incremental as it builds on existing sampling methods.
The paper tackled the problem of out-of-distribution generalization in chest X-ray pathology prediction by proposing a balanced batch sampling technique, which improved performance over baseline models without balancing.
Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge. There have been several proposals for efficient and robust visual representation learning among vision research practitioners, especially in the sensitive and critical biomedical domain. In this paper, we propose an idea for out-of-distribution generalization of chest X-ray pathologies that uses a simple balanced batch sampling technique. We observed that balanced sampling between the multiple training datasets improves the performance over baseline models trained without balancing.