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. Structured Learning and Prediction in Computer Vision introduces the reader to the most popular classes of structured models in computer vision. The focus is on discrete undirected graphical models which are covered in detail together with a description of algorithms for both probabilistic inference and maximum a posteriori inference. It also discusses separately recently successful techniques for prediction in general structured models. The second part of Structured Learning and Prediction in Computer Vision describes methods for parameter learning, distinguishing the classic maximum likelihood based methods from the more recent prediction-based parameter learning methods. It highlights developments to enhance current models and discusses kernelized models and latent variable models. Throughout Structured Learning and Prediction in Computer Vision the main text is interleaved with successful computer vision applications of the explained techniques. For convenience the reader can find a summary of the notation used at the end of the book.

An up-to-date account of the interplay between optimization and machine learning, accessible to students and researchers in both communities. The interplay between optimization and machine learning is one of the most important developments in modern computational science. Optimization formulations and methods are proving to be vital in designing algorithms to extract essential knowledge from huge volumes of data. Machine learning, however, is not simply a consumer of optimization technology but a rapidly evolving field that is itself generating new optimization ideas. This book captures the state of the art of the interaction between optimization and machine learning in a way that is accessible to researchers in both fields. Optimization approaches have enjoyed prominence in machine learning because of their wide applicability and attractive theoretical properties. The increasing complexity, size, and variety of today's machine learning models call for the reassessment of existing assumptions. This book starts the process of reassessment. It describes the resurgence in novel contexts of established frameworks such as first-order methods, stochastic approximations, convex relaxations, interior-point methods, and proximal methods. It also devotes attention to newer themes such as regularized optimization, robust optimization, gradient and subgradient methods, splitting techniques, and second-order methods. Many of these techniques draw inspiration from other fields, including operations research, theoretical computer science, and subfields of optimization. The book will enrich the ongoing cross-fertilization between the machine learning community and these other fields, and within the broader optimization community.