The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging
TAP-JEPA is introduced, a ViT-B/3D trained on 113,611 CT volumes that is competitive with state-of-the-art encoders in scan-level classification and shows that contextual predictability is not a sufficient proxy for clinical relevance in medical representation learning.
F. Drexel, B. Kainz, J. Kather et al.
· 0 citations