Efficient and accurate approximations of nonlinear convolutional networks

• Published in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1984 - 1992
• Main Authors: Zhang, Xiangyu, Zou, Jianhua, Ming, Xiang, He, Kaiming, Sun, Jian
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2015
• Subjects: Acceleration; Accuracy; Approximation; Approximation methods; Complexity theory; Computational modeling; Computer vision; Conferences; Errors; Matrix decomposition; Networks; Neural networks; Nonlinearity; Pattern recognition; Principal component analysis
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2015.7298809

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We minimize the reconstruction error of the nonlinear responses, subject to a low-rank constraint which helps to reduce the complexity of filters. We develop an effective solution to this constrained nonlinear optimization problem. An algorithm is also presented for reducing the accumulated error when multiple layers are approximated. A whole-model speedup ratio of 4× is demonstrated on a large network trained for ImageNet, while the top-5 error rate is only increased by 0.9%. Our accelerated model has a comparably fast speed as the "AlexNet" [11], but is 4.7% more accurate.