VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing

Autor:	Zhang, Qian, Li, Jianjun, Yao, Meng, Song, Liangchen, Zhou, Helong, Li, Zhichao, Meng, Wenming, Zhang, Xuezhi, Wang, Guoli
Rok vydání:	2019
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	In this paper, we propose a novel network design mechanism for efficient embedded computing. Inspired by the limited computing patterns, we propose to fix the number of channels in a group convolution, instead of the existing practice that fixing the total group numbers. Our solution based network, named Variable Group Convolutional Network (VarGNet), can be optimized easier on hardware side, due to the more unified computing schemes among the layers. Extensive experiments on various vision tasks, including classification, detection, pixel-wise parsing and face recognition, have demonstrated the practical value of our VarGNet. Comment: Technical report
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1907.05653 Zobrazit plný text záznamu View this record from Arxiv