Structured Learning and Prediction in Computer Vision

Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structure reflecting task-specific relations and constraints. This tutorial introduces the reader to the most popular classes of structured models in computer vision. Our focus is discrete undirected graphical models which we cover in detail together with a description of algorithms for both probabilistic inference and maximum a posteriori inference. We discuss separately recently successful techniques for prediction in general structured models. In the second part of this tutorial we describe methods for parameter learning where we distinguish the classic maximum likelihood based methods from the more recent prediction-based parameter learning methods. We highlight developments to enhance current models and discuss kernelized models and latent variable models. To make the tutorial practical and to provide links to...

• Type: Journal
• Year: 2011
• Where: FTCGV
• Authors: Sebastian Nowozin, Christoph H. Lampert
• Keywords: Computer Vision Literature, Cryptology, FTCGV 2011, Latent Variable Models, Probabilistic Inference