Learning Filter Basis for Convolutional Neural Network Compression

Yawei Li, Shuhang Gu, Luc Van Gool, Radu Timofte; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 5623-5632

Abstract


Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers. Moreover, quite a large number of filters are also used for a single convolutional layer, which exaggerates the parameter burden of current methods. Thus, in this paper, we try to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers. For the forward pass, the learned basis is used to approximate the original filters and then used as parameters for the convolutional layers. We validate our proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks and compare favorably to the existing state-of-the-art in terms of reduction of parameters and preservation of accuracy. Code is available at https://github.com/ofsoundof/learning_filter_basis

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Li_2019_ICCV,
author = {Li, Yawei and Gu, Shuhang and Gool, Luc Van and Timofte, Radu},
title = {Learning Filter Basis for Convolutional Neural Network Compression},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}