DeepBE: Learning Deep Binary Encoding for Multi-Label Classification

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	DeepBE: Learning Deep Binary Encoding for Multi-Label Classification
	Li, Chenghua1,2 ; Kang, Qi 4; Ge, Guojing 1; Song, Qiang1,2 ; Lu, Hanqing1,2 ; Cheng, Jian1,2,3
	2016
会议日期	2016.6.27-6.30
会议地点	Las Vegas, NV, USA
关键词	Chalearn2016 Deepbe Multi-label Classification
英文摘要	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.
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/20140]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
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]. 见:. Las Vegas, NV, USA. 2016.6.27-6.30.