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
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.
条目包含的文件
条目无相关文件。
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
[Weiqiang Ren]的文章
[Yinan Yu]的文章
[Junge Zhang]的文章
百度学术
百度学术中相似的文章
[Weiqiang Ren]的文章
[Yinan Yu]的文章
[Junge Zhang]的文章
必应学术
必应学术中相似的文章
[Weiqiang Ren]的文章
[Yinan Yu]的文章
[Junge Zhang]的文章
相关权益政策
暂无数据
收藏/分享
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。