Unsupervised Structure Learning of Stochastic And-Or Grammars

Part of Advances in Neural Information Processing Systems 26 (NIPS 2013)

Bibtex Metadata Paper Reviews Supplemental


Kewei Tu, Maria Pavlovskaia, Song-Chun Zhu


Stochastic And-Or grammars compactly represent both compositionality and reconfigurability and have been used to model different types of data such as images and events. We present a unified formalization of stochastic And-Or grammars that is agnostic to the type of the data being modeled, and propose an unsupervised approach to learning the structures as well as the parameters of such grammars. Starting from a trivial initial grammar, our approach iteratively induces compositions and reconfigurations in a unified manner and optimizes the posterior probability of the grammar. In our empirical evaluation, we applied our approach to learning event grammars and image grammars and achieved comparable or better performance than previous approaches.