DeepBE: Learning Deep Binary Encoding for Multi-Label Classification | |
Li, Chenghua1,2![]() ![]() ![]() | |
2016 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition Workshop |
会议日期 | 2016.6.27-6.30 |
会议地点 | Las Vegas, NV, USA |
摘要 | The track 2 and track 3 of ChaLearn 2016 can be considered as Multi-Label Classification problems. We present a framework of learning deep binary encoding (DeepBE) to deal with multi-label problems by transforming multi-labels to single labels. The transformation of DeepBE is in a hidden pattern, which can be well addressed by deep convolutions neural networks (CNNs). Furthermore, we adopt an ensemble strategy to enhance the learning robustness. This strategy is inspired by its effectiveness in fine-grained image recognition (FGIR) problem, while most of face related tasks such as track 2 and track 3 are also FGIR problems. By DeepBE, we got 5.45% and 10.84% mean square error for track 2 and track 3 respectively. Additionally, we proposed an algorithm adaption method to treat the multiplelabels of track 2 directly and got 6.84% mean square error. |
关键词 | Chalearn2016 Deepbe Multi-label Classification |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20140 |
专题 | 模式识别国家重点实验室_图像与视频分析 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.University of Chinese Academy of Sciences 3.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences 4.Beijing Institute Of Technology |
推荐引用方式 GB/T 7714 | Li, Chenghua,Kang, Qi,Ge, Guojing,et al. DeepBE: Learning Deep Binary Encoding for Multi-Label Classification[C],2016. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
DeepBE Learning Deep(3165KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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