Learning Disentangled Representations in the Imaging Domain
It addresses the problem of data scarcity and annotation costs for researchers and practitioners in fields like medical imaging and computer vision, but is incremental as it surveys existing work.
This tutorial paper reviews the motivation, concepts, and methods for learning disentangled representations in imaging, highlighting their potential to reduce data and annotation needs in computer vision and healthcare applications.
Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using modest amounts of data, or used directly in unseen domains achieving remarkable performance in the corresponding task. This alleviation of the data and annotation requirements offers tantalising prospects for applications in computer vision and healthcare. In this tutorial paper, we motivate the need for disentangled representations, revisit key concepts, and describe practical building blocks and criteria for learning such representations. We survey applications in medical imaging emphasising choices made in exemplar key works, and then discuss links to computer vision applications. We conclude by presenting limitations, challenges, and opportunities.