Speaker: Sanja Fidler
Department of Computer Science, UofT
Title: Learning a Hierarchical Compositional Shape Vocabulary for Multi-class Object Representation
Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a higher number of object classes. In this talk I will present our framework for learning a hierarchical compositional shape vocabulary for representing multiple object classes. The approach takes simple contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class-specific shape compositions, each exerting a high degree of shape variability. In the top-level of the vocabulary, the compositions are sufficiently large and complex to represent the whole shapes of the objects. The experimental results show that the learned multi-class object representation scales sublinearly with the number of object classes and achieves a state-of-the-art detection performance at both, faster inference as well as shorter training times.