Efficient Feature Coding Based on Auto-encoder Network for Image Classification

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Efficient Feature Coding Based on Auto-encoder Network for Image Classification
	Xie, Guo-Sen; Zhang, Xu-Yao; Liu, Cheng-Lin
	2014
会议名称	Asian Conference on Computer Vision
会议录名称	Procceding of ACCV 2014
会议日期	2014-11
会议地点	新加坡
摘要	Local descriptor coding is one crucial step in traditional Bag of Words (BoW) framework for image categorization. However, the slow coding speed of previous methods is one limitation for applications in large scale problems. Recently, neural network based models have been widely applied in various classification tasks. Using neural network models for descriptor coding is straightforward and efficient due to their fast forward propagation. In this paper, we propose to use the Auto-Encoder (AE) network as a local descriptor coding block, and further embed AE network in the BoW framework for the purpose of image classification. To make the hidden activities of AE network to be both selective and sparse, we add an efficient and effective regularization term into the learning process of AE network, which can promote sparsity of the hidden layer for each input descriptor as well as the selectivity for each hidden node. By incorporating the AE network coding with the BoW framework, we can achieve better results and faster speeds than other state-of-theart feature coding methods on Caltech101, Scene15 and UIUC 8-Sports databases.
关键词	Feature Coding
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11957
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Xie, Guo-Sen
推荐引用方式 GB/T 7714	Xie, Guo-Sen,Zhang, Xu-Yao,Liu, Cheng-Lin. Efficient Feature Coding Based on Auto-encoder Network for Image Classification[C],2014.

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
ACCV 14.pdf（622KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载