Automated Multi-Stage Compression of Neural Networks

Julia Gusak, Maksym Kholiavchenko, Evgeny Ponomarev, Larisa Markeeva, Philip Blagoveschensky, Andrzej Cichocki, Ivan Oseledets; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0


Low-rank tensor approximations are very promising for compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.

Related Material

author = {Gusak, Julia and Kholiavchenko, Maksym and Ponomarev, Evgeny and Markeeva, Larisa and Blagoveschensky, Philip and Cichocki, Andrzej and Oseledets, Ivan},
title = {Automated Multi-Stage Compression of Neural Networks},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}