Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification

CASIA OpenIR > 智能感知与计算研究中心

	Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification
	Weiqiang Ren; Yinan Yu; Junge Zhang; Kaiqi Huang
	2014
会议名称	International Conference on Pattern Recognition
会议录名称	Proc. International Conference on Pattern Recognition 2014
页码	2938-2943
会议日期	2014-08-01
会议地点	Stockholm, Sweden
摘要	Learning low-dimensional feature representations is a crucial task in machine learning and computer vision. Recently the impressive breakthrough in general object recognition made by large scale convolutional networks shows that convolutional networks are able to extract discriminative hierarchical features in large scale object classification task. However, for vision tasks other than end-to-end classification, such as K Nearest Neighbor classification, the learned intermediate features are not necessary optimal for the specific problem. In this paper, we aim to exploit the power of deep convolutional networks and optimize the output feature layer with respect to the task of K Nearest Neighbor (kNN) classification. By directly optimizing the kNN classification error on training data, we in fact learn convolutional nonlinear features in a data-driven and task-driven way. Experimental results on standard image classification benchmarks show that the proposed method is able to learn better feature representations than other general end-to-end classification methods on kNN classification task.
关键词	Computer Vision convolution image Classification
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12685
专题	智能感知与计算研究中心
通讯作者	Kaiqi Huang
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Weiqiang Ren,Yinan Yu,Junge Zhang,et al. Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification[C],2014:2938-2943.