Category level object segmentation - learning to segment objects with latent aspect models

We propose a new method for learning to segment objects in images. This method is based on a latent variables model used for representing images and objects, inspired by the LDA model. Like the LDA model, our model is capable of automatically discovering which visual information comes from which object. We extend LDA by considering that images are made of multiple overlapping regions, treated as distinct documents, giving more chance to small objects to be discovered. This model is extremely well suited for assigning image patches to objects (even if they are small), and therefore for segmenting objects. We apply this method on objects belonging to categories with high intra-class variations and strong viewpoint changes.