Abstract

In this talk we’ll discuss Semantic Texton Forests, efficient and powerful new low-level features proposed recently at CVPR 2008 . These are ensembles of decision trees that act directly on image pixels, and therefore do not need the expensive computation of filter-bank responses or local descriptors. They are extremely fast to both train and test, especially compared with k-means clustering and nearest-neighbor assignment of feature descriptors, and the talk will be motivated with a real-time demo of object segmentation. The nodes in the trees provide (i) an implicit hierarchical clustering into semantic textons, and (ii) an explicit local classification estimate. A bag of semantic textons combines a histogram of semantic textons over an image region with a region prior category distribution. The bag of semantic textons is computed over the whole image for categorization, and over local rectangular regions for segmentation. Including both histogram and region prior allows our segmentation algorithm to exploit both textural and semantic context. Our third contribution is an image-level prior for segmentation that emphasizes those categories that the automatic categorization believes to be present. We evaluate on two datasets including the very challenging VOC 2007 segmentation dataset. Our results significantly improve segmentation accuracy, and more importantly drastically increase execution speed.