DeepBE: Learning Deep Binary Encoding for Multi-Label Classification
Li, Chenghua1,2; Kang, Qi4; Ge, Guojing1; Song, Qiang1,2; Lu, Hanqing1,2; Cheng, Jian1,2,3
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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Chenghua]的文章
[Kang, Qi]的文章
[Ge, Guojing]的文章
百度学术
百度学术中相似的文章
[Li, Chenghua]的文章
[Kang, Qi]的文章
[Ge, Guojing]的文章
必应学术
必应学术中相似的文章
[Li, Chenghua]的文章
[Kang, Qi]的文章
[Ge, Guojing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: DeepBE Learning Deep Binary Encoding for Multi-Label Classification.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。