Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)

—In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmentation can be regarded as a special data clustering problem where both class-specific information and local texture/color similarities have to be considered. To this end, we propose a hybrid graph model (HGM) that can make effective use of both symmetric and asymmetric relationship among samples. The vertices of a hybrid graph represent the samples and are connected by directed edges and/or undirected ones, which represent the asymmetric and/or symmetric relationship between them, respectively. When applied to object segmentation, vertices are superpixels, the asymmetric relationship is the conditional dependence of occurrence, and the symmetric relationship is the color/texture similarity. By combining the Markov chain formed by the directed subgraph and the minimal cut of the undirected subgraph, the object...

• Type: Journal
• Year: 2010
• Where: PAMI
• Authors: Guangcan Liu, Zhouchen Lin, Yong Yu, Xiaoou Tang
• Keywords: Asymmetric Relationship, Hybrid Graph, Object Segmentation, PAMI 2010