arXiv Analytics

Sign in

arXiv:1511.06067 [cs.LG]AbstractReferencesReviewsResources

Convolutional neural networks with low-rank regularization

Cheng Tai, Tong Xiao, Xiaogang Wang, Weinan E

Published 2015-11-19Version 1

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank tensor decomposition for removing the redundancy in the convolution kernels. The algorithm finds the exact global optimizer of the decomposition and is more effective than iterative methods. Based on the decomposition, we further propose a new method for training low-rank constrained CNNs from scratch. Interestingly, while achieving a significant speedup, sometimes the low-rank constrained CNNs delivers significantly better performance than their non-constrained counterparts. On the CIFAR-10 dataset, the proposed low-rank NIN model achieves $91.31\%$ accuracy, which also improves upon state-of-the-art result. We evaluated the proposed method on CIFAR-10 and ILSVRC12 datasets for a variety of modern CNNs, including AlexNet, NIN, VGG and GoogleNet with success. For example, the forward time of VGG-16 is reduced by half while the performance is still comparable. Empirical success suggests that low-rank tensor decompositions can be a very useful tool for speeding up large CNNs.

Related articles: Most relevant | Search more
arXiv:1809.10463 [cs.LG] (Published 2018-09-27)
Learning to Train a Binary Neural Network
arXiv:1905.04967 [cs.LG] (Published 2019-05-13)
Implicit Filter Sparsification In Convolutional Neural Networks
arXiv:1707.09641 [cs.LG] (Published 2017-07-30)
Visual Explanations for Convolutional Neural Networks via Input Resampling