The performance of machine learning methods is heavily dependent on the choice of data representation. In real world applications such as scene recognition problems, the widely used low-level input features can fail to explain the high-level semantic label concepts. In this work, we address this problem by proposing a novel patch- based latent variable model to integrate latent contextual representation learning and classification model training in one joint optimization framework. Within this framework, the latent layer of variables bridge the gap between inputs and outputs by providing discriminative explanations for the semantic output labels, while being predictable from the low-level input features. Experiments conducted on standard scene recog-nition tasks demonstrate the efficacy of the proposed approach, comparing to the state-of-the-art scene recognition methods.

31st International Conference on Machine Learning, ICML 2014
School of Computer Science

Li, X. (Xin), & Guo, Y. (2014). Latent semantic representation learning for scene classification. In 31st International Conference on Machine Learning, ICML 2014 (pp. 1928–1936).