Skip to contentSkip to filters

We use cookies for analytics.

Towards Understanding Transfer Learning with Applications to Medical Imaging

Maithra Raghu

Cornell University & Google Brain

Recording

46 min

Abstract

Maithra Raghu surveys what pretraining transfers when a network is fine-tuned on another task. She compares evidence from natural and medical images, where differences in the data and tasks challenge standard intuitions about feature reuse. The talk examines the role of model size, the performance of lightweight architectures, and improvements that can occur independently of the transferred features.

Topics