Learning Deep Structured Models

[edit]

Liang-Chieh Chen, Alexander Schwing, Alan Yuille, Raquel Urtasun ;
Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:1785-1794, 2015.

Abstract

Many problems in real-world applications involve predicting several random variables that are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such dependencies. The goal of this paper is to combine MRFs with deep learning to estimate complex representations while taking into account the dependencies between the output random variables. Towards this goal, we propose a training algorithm that is able to learn structured models jointly with deep features that form the MRF potentials. Our approach is efficient as it blends learning and inference and makes use of GPU acceleration. We demonstrate the effectiveness of our algorithm in the tasks of predicting words from noisy images, as well as tagging of Flickr photographs. We show that joint learning of the deep features and the MRF parameters results in significant performance gains.

Related Material