Medical foundation models converge less under label supervision

Excerpt

arXiv:2607.20274v2 Announce Type: replace-cross Abstract: Diagnostic classifiers and imaging biomarkers are fitted on the embeddings of medical foundation models. These models are replaced as new versions appear. This practice assumes that different models represent images alike. We tested this assumption with more than 750,000 images from 14 datasets in five imaging modalities, 18 public models, and 101 models trained on chest radiographs and histopathology that differ in pretraining objective,