Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes

We develop a statistical framework for the simultaneous, unsupervised segmentation and discovery of visual object categories from image databases. Examining a large set of manually segmented scenes, we show that object frequencies and segment sizes both follow power law distributions, which are well modeled by the Pitman

• Type: Conference
• Year: 2008
• Where: NIPS
• Authors: Erik B. Sudderth, Michael I. Jordan
• Keywords: Information Technology, NIPS 2008, Nonparametric Prior Distribution, Unsupervised Segmentation, Visual Object Categories