 |
    |
Architectural Style Classification Using Multinomial Latent Logistic Regression*
Zhe Xu1, 2, Dacheng Tao2, Ya Zhang1, Junjie Wu3, and Ah Chung Tsoi4
1Shanghai Key Laboratory of Multimedia Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China
2Centre for Quantum Computation & Intelligent Systems and Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW, Australia
3School of Economics and Management, Beihang University, Beijing, China
4Faculty of Information Technology, Macau University of Science and Technology, Macau, China
Abstract. Architectural style classification differs from standard classification tasks due to the rich inter-class relationships between different 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 propose 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 release a new large-scale architectural style dataset containing twenty-five classes. Experimentation on this dataset shows that MLLR in combination 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.
Keywords: Latent Variable Models, Architectural Style Classification, Architectural Style Dataset
Electronic Supplementary Material:
LNCS 8689, p. 600 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014