Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images

Abstract

In this paper we address the memory demands that come with the processing of 3-dimensional, high-resolution, multi-channeled medical images in deep learning. We exploit memory-efficient backpropagation techniques, to reduce the memory complexity of network training from being linear in the network's depth, to being roughly constant $-$ permitting us to elongate deep architectures with negligible memory increase. We evaluate our methodology in the paradigm of Image Quality Transfer, whilst noting its potential application to various tasks that use deep learning. We study the impact of depth on accuracy and show that deeper models have more predictive power, which may exploit larger training sets. We obtain substantially better results than the previous state-of-the-art model with a slight memory increase, reducing the root-mean-squared-error by $13\%$. Our code is publicly available.

Accepted in: MICCAI 2018

References in corpus (6)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• The Loss Surfaces of Multilayer Networks
• Training Deep Nets with Sublinear Memory Cost
• The Reversible Residual Network: Backpropagation Without Storing Activations
• Reversible Architectures for Arbitrarily Deep Residual Neural Networks
• Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution