卷积(计算机科学)
卷积神经网络
计算机科学
可分离空间
奇异值分解
人工智能
推论
模式识别(心理学)
分解
频道(广播)
算法
人工神经网络
数学
计算机网络
生物
数学分析
生态学
作者
Yihui He,Jianing Qian,Jianren Wang
出处
期刊:Cornell University - arXiv
日期:2019-01-01
被引量:5
标识
DOI:10.48550/arxiv.1910.09455
摘要
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%.
科研通智能强力驱动
Strongly Powered by AbleSci AI