Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images
This addresses memory constraints for researchers and practitioners in medical imaging using deep learning, though it is incremental as it builds on existing memory-efficient techniques.
The paper tackles the high memory demands of training deep neural networks on 3D medical images by using memory-efficient backpropagation to reduce memory complexity from linear to roughly constant with depth, enabling deeper models that achieve a 13% reduction in root-mean-squared-error compared to previous state-of-the-art.
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.