We propose a novel method for unsupervised class segmen- tation on a set of images. It alternates between segmenting object in- stances and learning a class model. The method is based on a segmen- tation energy dened over all images at the same time, which can be optimized eciently by techniques used before in interactive segmenta- tion. Over iterations, our method progressively learns a class model by integrating observations over all images. In addition to appearance, this model captures the location and shape of the class with respect to an automatically determined coordinate frame common across images. This frame allows us to build stronger shape and location models, similar to those used in object class detection. Our method is inspired by inter- active segmentation methods , but it is fully automatic and learns models characteristic for the object class rather than specic to one par- ticular object/image. We experimentally demonstrate on the Caltech4, Caltech101, and Weizmann horses datasets that our method (a) trans- fers class knowledge across images and this improves results compared to segmenting every image independently; (b) outperforms Grabcut  for the task of unsupervised segmentation; (c) oers competitive per- formance compared to the state-of-the-art in unsupervised segmentation and in particular it outperforms the topic model .