Unsupervised Learning of Dictionaries of Hierarchical Compositional Models

Abstract

This paper proposes an unsupervised method for learning dictionaries of hierarchical compositional models for representing natural images. Each model is in the form of a template that consists of a small group of part templates that are allowed to shift their locations and orientations relative to each other, and each part template is in turn a composition of Gabor wavelets that are also allowed to shift their locations and orientations relative to each other. Given a set of unannotated training images, a dictionary of such hierarchical templates are learned so that each training image can be represented by a small number of templates that are spatially translated, rotated and scaled versions of the templates in the learned dictionary. The learning algorithm iterates between the following two steps: (1) Image encoding by a template matching pursuit process that involves a bottom-up template matching sub-process and a top-down template localization sub-process. (2) Dictionary re-learning by a shared matching pursuit process. Experimental results show that the proposed approach is capable of learning meaningful templates, and the learned templates are useful for tasks such as domain adaption and image cosegmentation.

Greedy Structure Learning of Hierarchical Compositional Models

“…The Active Basis Model [34] is a deformable object model that is formulated within an elegant information-theoretic framework and, in addition to shape deformations, also models the object's appearance. In this work, we use the hierarchical compositional generalization of the Active Basis Model [5] as object representation.…”

“…Therefore they are limited in terms of their ability to model large object deformations and strong appearance changes [5]. In the next section, we introduce Compositional Active Basis Models [5] which overcome this limitation by introducing hierarchical relations between the basis filters. [5].…”

“…In the next section, we introduce Compositional Active Basis Models [5] which overcome this limitation by introducing hierarchical relations between the basis filters. [5]. Note the tree-like dependency structure between the variables which enables a fast posterior inference via dynamic programming.…”

“…A1 The structure of the object is known a-priori, in terms of the number of parts and their hierarchical relation [39,5] (Figure 1b).…”

A Simple Stochastic Algorithm for Structural Features Learning

“…Furthermore, its individual learned compositions can be used as features in more sophisticated classification framework such as SVM or AdaBoost. Similar approach [11] has been recently shown to be very efficient in domain transfer task 1 . This indicates that structural approach has very good generalization capabilities.…”