Search Machine Learning Repository:
Latent Semantic Representation Learning for Scene Classification
Authors: Xin Li and Yuhong Guo
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Abstract: 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 recognition tasks demonstrate the efficacy of the proposed approach, comparing to the state-of-the-art scene recognition methods.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).