Knowledge Commons of Institute of Automation，CAS
| Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review | |
| Tomaso Poggio1; Hrushikesh Mhaskar2,3; Lorenzo Rosasco1; Brando Miranda1; Qianli Liao1 | |
| Source Publication | International Journal of Automation and Computing
 |
| ISSN | 1476-8186 |
| 2017 | |
| Volume | 14Issue:5Pages:503-519 |
| Subtype | IJAC-HIC-2016-11-271.pdf |
| Abstract | 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. |
| Keyword | Deep learning fine-grained image classification semantic segmentation convolutional neural network (CNN) recurrent neural network (RNN). |
| DOI | 10.1007/s11633-017-1054-2 |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/42475 |
| Collection | 学术期刊_International Journal of Automation and Computing |
| Affiliation | 1.Center for Brains, Minds, and Machines, McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA 2.Department of Mathematics, California Institute of Technology, Pasadena, CA 91125, USA 3.Institute of Mathematical Sciences, Claremont Graduate University, Claremont, CA 91711, USA |
| Recommended Citation 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. |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
| IJAC-HIC-2016-11-271（1711KB） | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | View Download | |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment