The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging

The paper introduces TAP-JEPA, a joint‑embedding predictive architecture trained on over 113,000 CT volumes, which achieves performance comparable to leading encoders in scan‑level classification. It demonstrates a predictability bias: while anatomy is largely predictable from context, pathology is not, leading to significant degradation in pathology detection when predictions are applied. The study audits the model’s predictive pathway, showing that pathology representations shift toward control regions and that removing pathology tokens minimally affects downstream decisions, underscoring that contextual predictability alone is insufficient for clinical relevance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• rag
• benchmarks
• safety