Discriminative Fields for Modeling Spatial Dependencies in Natural Images

In this paper we present Discriminative Random Fields (DRF), a discriminative framework for the classification of natural image regions by incorporating neighborhood spatial dependencies in the labels as well as the observed data. The proposed model exploits local discriminative models and allows to relax the assumption of conditional independence of the observed data given the labels, commonly used in the Markov Random Field (MRF) framework. The parameters of the DRF model are learned using penalized maximum pseudo-likelihood method. Furthermore, the form of the DRF model allows the MAP inference for binary classification problems using the graph min-cut algorithms. The performance of the model was verified on the synthetic as well as the real-world images. The DRF model outperforms the MRF model in the experiments.

[1]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[2]  Peter M. Williams,et al.  Bayesian Regularization and Pruning Using a Laplace Prior , 1995, Neural Computation.

[3]  Trevor J. Hastie,et al.  Discriminative vs Informative Learning , 1997, KDD.

[4]  Hui Cheng,et al.  Multiscale Bayesian segmentation using a trainable context model , 2001, IEEE Trans. Image Process..

[5]  Mário A. T. Figueiredo.  Adaptive Sparseness Using Jeffreys Prior , 2001, NIPS.

[6]  Michael I. Jordan,et al.  On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes , 2001, NIPS.

[7]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[8]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[9]  Christopher K. I. Williams,et al.  Combining Belief Networks and Neural Networks for Scene Segmentation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[11]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[12]  Martial Hebert,et al.  Man-made structure detection in natural images using a causal multiscale random field , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Chang-Tsun Li,et al.  A Class of Discrete Multiresolution Random Fields and Its Application to Image Segmentation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Martial Hebert,et al.  Discriminative random fields: a discriminative framework for contextual interaction in classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  R. Zabih,et al.  What energy functions can be minimized via graph cuts , 2004 .