2018/05/21 by Yoojin Choi, Choi, Yoojin, Mostafa El‐Khamy +3
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Sparse and Compressive Sensing Techniques
paper · pdf · doi:10.48550/arxiv.1805.08303
openalex publication_date 2018/05/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower complexity systems designed for Winograd convolution. Furthermore, we explore the universal quantization and compression of these networks. In particular, the proposed framework produces one compressed model whose convolutional filters can be made sparse either in the spatial domain or in the Winograd domain. Hence, one compressed model can be deployed universally on any platform, without need for re-training on the deployed platform, and the sparsity of its convolutional filters can be exploited for further complexity reduction in either domain. To get a better compression ratio, the sparse model is compressed in the spatial domain which has a less number of parameters. From our experiments, we obtain 24.2×, 47.7× and 35.4× compressed models for ResNet-18, AlexNet and CT-SRCNN, while their computational cost is also reduced by 4.5×, 5.1× and 23.5×, respectively.