Efficient Dilated-Winograd Convolutional Neural Networks

Dilated convolution is used to achieve wide receptive fields in computer vision algorithms such as image segmentation and denoising. Unlike the strided convolution, dilated convolution maintains the resolution of the output feature map same as the input feature map. Thus, the computational complexity can be increased to configure the convolutional neural network (CNN) architecture with the dilated convolutional layer. However, the complexity accordingly introduces additional computation delay and it is strongly required to have a proper way to lessen the computation delay of the dilated convolution. In this paper, we propose the dilated-Winograd convolution to reduce the computational complexity of the dilated convolution. By using the Winograd transform with a dilation rate, the number of pixels in the tile is effectively reduced. The proposed acceleration methods result in an average speedup of 2.043 and 1.456 with dilation rate of 2 and 4 compared to the state-of-the-art implementation.