Anisotropic Convolution for Image Classification | |
Li, Wenjuan; Li, Bing; Yuan, Chunfeng; Li, Yangxi; Wu, Haohao; Hu, Weiming; Wang, Fangshi | |
刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
2020-04-10 | |
卷号 | 29期号:99页码:5584-5595 |
关键词 | Anisotropic convolution image classification object localization |
ISSN号 | 1057-7149 |
DOI | 10.1109/TIP.2020.2985875 |
文献子类 | 期刊论文 |
英文摘要 | Convolutional neural networks are built upon simple but useful convolution modules. The traditional convolution has a limitation on feature extraction and object localization due to its fixed scale and geometric structure. Besides, the loss of spatial information also restricts the networks' performance and depth. To overcome these limitations, this paper proposes a novel anisotropic convolution by adding a scale factor and a shape factor into the traditional convolution. The anisotropic convolution augments the receptive fields flexibly and dynamically depending on the valid sizes of objects. In addition, the anisotropic convolution is a generalized convolution. The traditional convolution, dilated convolution and deformable convolution can be viewed as its special cases. Furthermore, in order to improve the training efficiency and avoid falling into a local optimum, this paper introduces a simplified implementation of the anisotropic convolution. The anisotropic convolution can be applied to arbitrary convolutional networks and the enhanced networks are called ACNs (anisotropic convolutional networks). Experimental results show that ACNs achieve better performance than many state-of-the-art methods and the baseline networks in tasks of image classification and object localization, especially in classification task of tiny images. |
URL标识 | 查看原文 |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/40605] |
专题 | 自动化研究所_模式识别国家重点实验室_视频内容安全团队 |
作者单位 | 1.PeopleAI, Inc. 2.National Computer Network Emergency Response Technical Team/Coordination Center of China (CNCERT/CC) 3.the State Key Laboratory of Communication Content Cognition, People’s Daily Online 4.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 5.School of Artificial Intelligence, University of Chinese Academy of Sciences 6.CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences 7.School of Software Engineering, Beijing Jiaotong University |
推荐引用方式 GB/T 7714 | Li, Wenjuan,Li, Bing,Yuan, Chunfeng,et al. Anisotropic Convolution for Image Classification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29(99):5584-5595. |
APA | Li, Wenjuan.,Li, Bing.,Yuan, Chunfeng.,Li, Yangxi.,Wu, Haohao.,...&Wang, Fangshi.(2020).Anisotropic Convolution for Image Classification.IEEE TRANSACTIONS ON IMAGE PROCESSING,29(99),5584-5595. |
MLA | Li, Wenjuan,et al."Anisotropic Convolution for Image Classification".IEEE TRANSACTIONS ON IMAGE PROCESSING 29.99(2020):5584-5595. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论