Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography
Rad-JEPA 3D, a joint-embedding predictive framework that learns volumetric CT representations by predicting the latent features of a complete scan from a masked view, is introduced and Hidden States Orthogonal Regularization (HSOR) is proposed, which aligns student-teacher hidden states and reduces feature redundancy throughout the encoder.