› Publications
› Software

Cite Details

Jiaming Liu, Yu Sun, Weijie Gan, Xiaojian Xu, Brendt Wohlberg and Ulugbek S. Kamilov, "SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees", IEEE Transactions on Computational Imaging, vol. 7, doi:10.1109/TCI.2021.3085534, pp. 598--610, Jun 2021


Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with the number of measurements, limiting their applicability to large-scale imaging inverse problems. We propose SGD-Net as a new methodology for improving the efficiency of deep unfolding through stochastic approximations of the data-consistency layers. Our theoretical analysis shows that SGD-Net can be trained to approximate batch deep unfolding networks to an arbitrary precision. Our numerical results on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the batch network at a fraction of training and testing complexity.

BibTeX Entry

author = {Jiaming Liu and Yu Sun and Weijie Gan and Xiaojian Xu and Brendt Wohlberg and Ulugbek S. Kamilov},
title = {{SGD-Net}: Efficient Model-Based Deep Learning with Theoretical Guarantees},
year = {2021},
month = Jun,
urlpdf = {},
urlhtml = {},
journal = {IEEE Transactions on Computational Imaging},
volume = {7},
doi = {10.1109/TCI.2021.3085534},
pages = {598--610}