中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
A Decomposable Winograd Method for N-D Convolution Acceleration in Video Analysis

文献类型：期刊论文

作者Huang, Di1,2,4; Zhang, Rui1,2; Zhang, Xishan1,2; Wu, Fan1,3,4; Wang, Xianzhuo1,2,4; Jin, Pengwei1,2,4; Liu, Shaoli1; Li, Ling3; Chen, Yunji2,4
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2021-08-04
页码21
关键词Convolution neural networks Model acceleration Winograd algorithm Video analysis
ISSN号0920-5691
DOI10.1007/s11263-021-01500-9
英文摘要Winograd's minimal filtering algorithm has been widely used in 2-D Convolutional Neural Networks (CNNs) to reduce the number of multiplications for faster processing. However, it is only effective on convolutions with kernel size as 3 and stride as 1, because it suffers from significantly increased FLOPs and numerical accuracy problems for kernel size larger than 3 and fails on convolution with stride larger than 1. Worse, the extension to N-D convolution will intensify the numerical accuracy problem. These problems severely obstruct Winograd's minimal filtering algorithm's application to video analysis. In this paper, we propose a novel Decomposable Winograd Method (DWM) for the N-D convolution acceleration, which breaks through the limitation of original Winograd's minimal filtering algorithm to more general convolutions. DWM decomposes kernels with large size or stride>1 to several small kernels with stride as 1 for further applying Winograd algorithm, so that DWMcan reduce the number of multiplications while keeping the numerical accuracy. It enables the fast exploration of larger kernel size, larger stride value, and higher dimensions in CNNs for high performance and accuracy and even the potential for new CNNs. Comparing against the original Winograd algorithm, the proposed DWM is able to support all kinds of N-D convolutions with a speedup of 1.44x-3.38x, without affecting the numerical accuracy.
资助项目Beijing Natural Science Foundation[JQ18013] ; NSF of China[61925208] ; NSF of China[61906179] ; NSF of China[62002338] ; NSF of China[61732007] ; NSF of China[61732002] ; NSF of China[U19B2019] ; NSF of China[U20A20227] ; Strategic Priority Research Program of Chinese Academy of Science[XDB 32050200] ; Strategic Priority Research Program of Chinese Academy of Science[XDC05010300] ; Beijing Academy of Artificial Intelligence (BAAI) ; Beijing Nova Program of Science and Technology[Z191100001119093] ; Youth Innovation Promotion Association CAS
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000681171700002
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/17394]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Rui
作者单位1.Cambricon Tech Ltd, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, SKL Comp Architecture, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Software, Beijing, Peoples R China
4.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Huang, Di,Zhang, Rui,Zhang, Xishan,et al. A Decomposable Winograd Method for N-D Convolution Acceleration in Video Analysis[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2021:21.
APA Huang, Di.,Zhang, Rui.,Zhang, Xishan.,Wu, Fan.,Wang, Xianzhuo.,...&Chen, Yunji.(2021).A Decomposable Winograd Method for N-D Convolution Acceleration in Video Analysis.INTERNATIONAL JOURNAL OF COMPUTER VISION,21.
MLA Huang, Di,et al."A Decomposable Winograd Method for N-D Convolution Acceleration in Video Analysis".INTERNATIONAL JOURNAL OF COMPUTER VISION (2021):21.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。