CASIA OpenIR  > 智能感知与计算研究中心
Online Codebook Reweighting Using Pairwise Constraints for Image Classification
Xin Zhao; Jianwei Ding; Kaiqi Huang; Tieniu Tan
2011
会议名称The First Asian Conference on Pattern Recognition
会议录名称Pattern Recognition, 2011
页码662-666
会议日期2011
会议地点Beijing, China
摘要Bag-of-words (BoW) model is widely used for image classification. Recently, the framework of sparse coding and max pooling proved an effective approach for image classification. Max pooling adopts a winner-take-all strategy. Thus, it can be regarded as a codebook weighting process. The results of this process are the weights of the associated codebook. However, there are high intra-class variations and strong background clutters in many image classification tasks. The weights obtained by max pooling only have limited information. This paper presents a codebook reweighting algorithm using pairwise constraints to improve the performance of sparse coding and max pooling framework. Pairwise constraints are the natural way of encoding the relationships between pairs of images. Therefore, the reweighted codebook is more effective to describe the relevance between pairs of images. An efficient online learning algorithm is presented based on passive-aggressive training strategy. We compare our method with other state-of-the-art methods on Graz-01 & 02 datasets. Experimental results illustrate the effectiveness and efficiency of our method for image classification.
关键词Clutter   image Classification   image Coding
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12695
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
Xin Zhao,Jianwei Ding,Kaiqi Huang,et al. Online Codebook Reweighting Using Pairwise Constraints for Image Classification[C],2011:662-666.
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
[Xin Zhao]的文章
[Jianwei Ding]的文章
[Kaiqi Huang]的文章
百度学术
百度学术中相似的文章
[Xin Zhao]的文章
[Jianwei Ding]的文章
[Kaiqi Huang]的文章
必应学术
必应学术中相似的文章
[Xin Zhao]的文章
[Jianwei Ding]的文章
[Kaiqi Huang]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。