Window Mining by Clustering Mid-Level Representation for Weakly Supervised Object Localization

CASIA OpenIR > 智能感知与计算研究中心

	Window Mining by Clustering Mid-Level Representation for Weakly Supervised Object Localization
	Chong Wang; Weiqiang Ren; Kaiqi Huang
	2014
会议名称	International Conference on Image Processing
会议录名称	Proc. International Conference on Image Processing 2014
页码	4067-4071
会议日期	2014-10-01
会议地点	Paris, France
摘要	Discovering positive detection windows in training images is a challenging problem in weakly supervised object detection. In this paper, we propose a window mining strategy by the simple and efficient k-means clustering. Firstly, a recent segmentation based object proposal is used for its highly semantic candidate windows; secondly, the bag-of-words model is adopted as mid-level object representation for each window. By clustering these windows with k-means, semantic clusters can be generated. Then, to discover the positive windows from these clusters, we further propose a cluster selection method based on each cluster's discrimination, which is evaluated by classification performance given the category label. With the semantic clusters, this selection process is effective and efficient. Evaluation on the challenging PASCAL VOC 2007 dataset shows that the proposed method outperforms all previous weakly supervised approaches.
关键词	Data Mining image Representation image Segmentation
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12682
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	Chong Wang,Weiqiang Ren,Kaiqi Huang. Window Mining by Clustering Mid-Level Representation for Weakly Supervised Object Localization[C],2014:4067-4071.