PANDA - Prototype-Anchored Alignment for Partially Unpaired Multimodal Learning, with Applications to Alzheimers MRI and TCGA Pathology
Read the original on arXiv Computer Vision →PANDA (Prototype‑Anchored Data Alignment) is a two‑stage framework that enables a primary‑modality model to benefit from auxiliary modalities even when those modalities are only partially paired or absent at inference. In Stage 1, a shared embedding is learned from the paired subset and class prototypes are estimated from the auxiliary data; in Stage 2, the primary encoder is trained on all subjects using cross‑entropy and alignment to the frozen prototypes. PANDA was evaluated on Alzheimer’s MRI and TCGA‑Lung pathology, achieving significant AUC gains and improved survival prediction while requiring no auxiliary inputs during deployment.
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 Computer Vision.