Structured Learning and Prediction in Computer VisionPowerful 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. |
Contents
Introduction | 1 |
2 | 12 |
Inference in Graphical Models | 21 |
Structured Prediction | 96 |
Conditional Random Fields | 127 |
Structured Support Vector Machines | 149 |
Prediction Problem | 171 |
Common terms and phrases
algorithm approximate argmax argmin binary computer vision conditional likelihood Conditional Random Fields constraints convergence convex define efficiently energy function estimate evaluation factor graph feasible set feature map foreground Gibbs sampler global gradient descent graph cuts graphical models image segmentation Input kernel label Lagrangian relaxation latent variables learned weight vector loopy belief propagation loss function loss-augmented prediction MAP inference Markov chain maximization mean field method minimization neighborhood objective function observed obtain optimal solution optimization problem p(yx pairwise terms parameter learning parameterized perceptron pixel PL training prediction function prediction problem prediction-based probabilistic inference probability distribution S-SVM training sample sb.t shown in Figure simulated annealing solve step structured perceptron structured prediction structured support vector subgradient subgradient method subset support vector machine task techniques tion tractable training examples training set typically unary factors upper bound Wcur Weur