Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review

doi:10.1007/s11633-017-1054-2

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review
	Tomaso Poggio 3; Hrushikesh Mhaskar 1,2; Lorenzo Rosasco 3; Brando Miranda 3; Qianli Liao 3
刊名	International Journal of Automation and Computing
	2017
卷号	14 期号:5 页码:503-519
关键词	Deep learning fine-grained image classification semantic segmentation convolutional neural network (CNN) recurrent neural network (RNN).
ISSN号	1476-8186
DOI	10.1007/s11633-017-1054-2
文献子类	IJAC-HIC-2016-11-271.pdf
英文摘要	The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to ¯ne-grained image classi¯cation which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks (CNNs), part detection based, ensemble of networks based and visual attention based ¯ne-grained image classi¯cation approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42475]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	1.Institute of Mathematical Sciences, Claremont Graduate University, Claremont, CA 91711, USA 2.Department of Mathematics, California Institute of Technology, Pasadena, CA 91125, USA 3.Center for Brains, Minds, and Machines, McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
推荐引用方式 GB/T 7714	Tomaso Poggio,Hrushikesh Mhaskar,Lorenzo Rosasco,et al. Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review[J]. International Journal of Automation and Computing,2017,14(5):503-519.
APA	Tomaso Poggio,Hrushikesh Mhaskar,Lorenzo Rosasco,Brando Miranda,&Qianli Liao.(2017).Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review.International Journal of Automation and Computing,14(5),503-519.
MLA	Tomaso Poggio,et al."Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review".International Journal of Automation and Computing 14.5(2017):503-519.