Deep Representation Learning with Target Coding
文献类型：会议论文
| 作者 | Shuo Yang; Ping Luo; Chen Change Loy; Kenneth W. Shum; Xiaoou Tang |
| 出版日期 | 2015 |
| 会议名称 | Association for the Advancement of Artificial Intelligence(AAAI) |
| 会议地点 | 美国田纳西奥斯汀 |
| 英文摘要 | We consider the problem of learning deep representation when target labels are available. In this paper,we show that there exists intrinsic relationship between target coding and feature representation learning in deep networks. Specifically, we found that distributed binary code with error correcting capability is more capable of encouraging discriminative features, in comparison to the 1-of-K coding that is typically used in supervised deep learning. This new finding reveals additional benefit of using error-correcting code for deep model learning, apart from its well-known error correcting property. Extensive experiments are conducted on popular visual benchmark datasets. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6693]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | Shuo Yang,Ping Luo,Chen Change Loy,et al. Deep Representation Learning with Target Coding[C]. 见:Association for the Advancement of Artificial Intelligence(AAAI). 美国田纳西奥斯汀. |
入库方式： OAI收割
来源：深圳先进技术研究院
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。