A discriminative graph inferring framework towards weakly supervised image parsing

详细信息    查看全文

• 作者：Lei Yu ; Bing-Kun Bao ; Changsheng Xu
• 关键词：Image annotation ; Appearance model ; Label propagation ; Label localization ; Image parsing
• 刊名：Multimedia Systems
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：23
• 期：1
• 页码：5-18
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems; Computer Communication Networks; Operating Systems; Data Storage Representation; Data Encryption; Computer Graphics;
• 出版者：Springer Berlin Heidelberg
• ISSN：1432-1882
• 卷排序：23

文摘

In this paper, we focus on the task of assigning labels to the over-segmented image patches in a weakly supervised manner, in which the training images contain the labels but do not have the labels’ locations in the images. We propose a unified discriminative graph inferring framework by simultaneously inferring patch labels and learning the patch appearance models. On one hand, graph inferring reasons the patch labels by a graph propagation procedure. The graph is constructed by connecting the nearest neighbors which share the same image label, and multiple correlations among patches and image labels are imposed as constraints to the inferring. On the other hand, for each label, the patches which do not contain the target label are adopted as negative samples to learn the appearance model. In this way, the predicted labels will be more accurate in the propagation. Graph inferring and the learned patch appearance models are finally embedded to complement each other in one unified formulation. Experiments on three public datasets demonstrate the effectiveness of our method in comparison with other baselines.