Prior Learning and Gibbs Reaction-Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
International Journal of Computer Vision
Convergent Tree-Reweighted Message Passing for Energy Minimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Online Learning for Matrix Factorization and Sparse Coding
The Journal of Machine Learning Research
Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
On parameter learning in CRF-based approaches to object class image segmentation
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
IEEE Transactions on Image Processing
Loss-specific training of non-parametric image restoration models: a new state of the art
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Hi-index | 0.00 |
Conditional Random Fields (CRFs) are popular models in computer vision for solving labeling problems such as image denoising. This paper tackles the rarely addressed but important problem of learning the full form of the potential functions of pairwise CRFs. We examine two popular learning techniques, maximum likelihood estimation and maximum margin training. The main focus of the paper is on models such as pairwise CRFs, that are simplistic (misspecified) and do not fit the data well. We empirically demonstrate that for misspecified models maximum-margin training with MAP prediction is superior to maximum likelihood estimation with any other prediction method. Additionally we examine the common belief that MLE is better at producing predictions matching image statistics.