Transfusion: Understanding Transfer Learning for Medical Imaging
Preprint
Abstract
Transfer learning from natural image datasets, particularly ImageNet, using standard large models and corresponding pretrained weights has become a de-facto method for deep learning applications to medical imaging. However, there are fundamental differences in data sizes, features and task specifications between natural image classification and the target medical tasks, and there is little understanding of the effects of transfer. In this paper, we explore properties of transfer learning for medical imaging. A performance evaluation on two large scale medical imaging tasks shows that surprisingly, transfer offers little benefit to performance, and simple, lightweight models can perform comparably to ImageNet architectures. Investigating the learned representations and features, we find that some of the differences from transfer learning are due to the over-parametrization of standard models rather than sophisticated feature reuse. We isolate where useful feature reuse occurs, and outline the implications for more efficient model exploration. We also explore feature independent benefits of transfer arising from weight scalings.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Rethinking ImageNet Pre-Training2019
- High-performance medicine: the convergence of human and artificial intelligenceNature Medicine, 2019
- Investigating Multilingual NMT Representations at Scale2019
- The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives2019
- Understanding Learning Dynamics Of Language Models with2019
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep LearningInvestigative Ophthalmology & Visual Science, 2016
- Diabetic retinopathy – Biomolecules and multiple pathophysiologyDiabetes & Metabolic Syndrome: Clinical Research & Reviews, 2015