Transfer classification for distinct manifestations with shared information
文献类型：会议论文
| 作者 | Qi, Lu ; Yin, Peijie; Huang, Xiayuan; Chen, Ken; Qiao, Hong
|
| 出版日期 | 2016 |
| 会议名称 | 12th World Congress on Intelligent Control and Automation (WCICA) |
| 会议日期 | JUN 12-15, 2016 |
| 会议地点 | Guilin, PEOPLES R CHINA |
| 关键词 | VISUAL-CORTEX |
| 通讯作者 | Qi, L |
| 英文摘要 | An object often has many distinct manifestations in computer vision, which brings a great challenge to utilizing more comprehensive information. Inspired by some biological researches about edge sensitivity and global structure priority, our key insight is to establish unified transfer classification network withshared contour information. Combining two convolutional networks with three cascaded filters, we build a unified kernel SVM classifier based on shared contour features. Two convolutional networks are usedfor acquiring the contour information of objects exactly. Obtained by three cascaded filters, sharededge features are used by a unified kernels SVM classifier. Our transfer classification network(TCN) is trained and tested with distinct manifestations including real photos(imagenet dataset or cifar-10 dataset) and cartoon abstracts. The model is able to extract robust contour features and achieve considerable transfer recognition accuracy(40% relative improvement to some popular convolutional models). |
| 会议录 | PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA)
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12827]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 自动化研究所_复杂系统管理与控制国家重点实验室 |
| 推荐引用方式 GB/T 7714 | Qi, Lu,Yin, Peijie,Huang, Xiayuan,et al. Transfer classification for distinct manifestations with shared information[C]. 见:12th World Congress on Intelligent Control and Automation (WCICA). Guilin, PEOPLES R CHINA. JUN 12-15, 2016. |
入库方式： OAI收割
来源：自动化研究所
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。