Factorized Convolutional Neural Networks

Min Wang, Baoyuan Liu, Hassan Foroosh; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 545-553

In this paper, we propose to factorize the standard convolutional layer to reduce the computation. The 3D convolution operation in a convolutional layer can be considered as performing spatial convolution in each channel and linear projection across channels simultaneously. By unravelling them and arranging the spatial convolution sequentially, each layer is composed of a low-cost single intra-channel convolution and a linear channel projection. When combined with residual connection, it can effectively preserve the spatial information and maintain the accuracy with significantly less computation. We also introduce a topological subdivisioning to reduce the connection between the input and output channels. Our experiments demonstrate that the proposed layers outperform the standard convolutional layers on performance/complexity ratio. Our models achieve similar performance to VGG-16, ResNet-34, ResNet-50, ResNet-101 while requiring 42x,7.32x, 4.38x, 5.85x less computation respectively.