Abstract
Architectural style classification differs from standard clas- sification tasks due to the rich inter-class relationships between differ- ent styles, such as re-interpretation, revival, and territoriality. In this paper, we adopt Deformable Part-based Models (DPM) to capture the morphological characteristics of basic architectural components and pro- pose Multinomial Latent Logistic Regression (MLLR) that introduces the probabilistic analysis and tackles the multi-class problem in latent variable models. Due to the lack of publicly available datasets, we re- lease a new large-scale architectural style dataset containing twenty-five classes. Experimentation on this dataset shows that MLLR in combina- tion with standard global image features, obtains the best classification results. We also present interpretable probabilistic explanations for the results, such as the styles of individual buildings and a style relationship network, to illustrate inter-class relationships.