Learning Deep Structured Models
This work addresses the challenge of structured prediction in real-world applications, such as image analysis, by integrating deep learning with probabilistic graphical models, though it appears incremental as it builds on existing MRF and deep learning methods.
The paper tackles the problem of predicting multiple statistically related random variables by combining Markov random fields with deep learning to estimate complex representations while accounting for output dependencies, resulting in significant performance gains in tasks like word prediction from noisy images and multi-class classification of Flickr photographs.
Many problems in real-world applications involve predicting several random variables which are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such relationships. The goal of this paper is to combine MRFs with deep learning algorithms 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 multi-class classification of Flickr photographs. We show that joint learning of the deep features and the MRF parameters results in significant performance gains.