Discriminative Random Fields

Abstract

Abstract.In this research we address the problem of classification and labeling of regions given a single static natural image. Natural images exhibit strong spatial dependencies, and modeling these dependencies in a principled manner is crucial to achieve good classification accuracy. In this work, we present Discriminative Random Fields (DRFs) to model spatial interactions in images in a discriminative framework based on the concept of Conditional Random Fields proposed by Lafferty et al (Lafferty et al., 2001). The DRFs classify image regions by incorporating neighborhood spatial interactions in the labels as well as the observed data. The DRF framework offers several advantages over the conventional Markov Random Field (MRF) framework. First, the DRFs allow to relax the strong assumption of conditional independence of the observed data generally used in the MRF framework for tractability. This assumption is too restrictive for a large number of applications in computer vision. Second, the DRFs derive their classification power by exploiting the probabilistic discriminative models instead of the generative models used for modeling observations in the MRF framework. Third, the interaction in labels in DRFs is based on the idea of pairwise discrimination of the observed data making it data-adaptive instead of being fixed a priori as in MRFs. Finally, all the parameters in the DRF model are estimated simultaneously from the training data unlike the MRF framework where the likelihood parameters are usually learned separately from the field parameters. We present preliminary experiments with man-made structure detection and binary image restoration tasks, and compare the DRF results with the MRF results.

Improved Hough transform by modeling context with conditional random fields for partially occluded pedestrian detection

“…It is widely used for image semantic segmentation and patch-level labeling [11][12][13][14][15]18 by addressing computer vision problems with CRF inference. Kumar and Hebert 18 proposed the discriminative random field, which inherits the CRF concept for labeling man-made structures at patch level. To disambiguate local image information, He et al 11 proposed a multi-CRF with three separate components at different scales for image semantic segmentation.…”

“…Fortunately, conditional random field (CRF) frameworks modeling context have achieved an impressive performance for semantic segmentation, [11][12][13][14][15] image classification, 16 saliency detection, 17 and object detection. 18 The CRF distribution can be formulated by a probabilistic graphical model, in which variables are interdependent rather than independent. Given an image, CRF inference is performed by a maximum a posteriori (MAP) or maximum posterior marginal criterion, and all patches can be classified into an object category or background simultaneously.…”

“…: E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 1 8 ; 6 3 ; 7 5 2 ¼ X i pðhjO n ; c i ;lÞpðO n jc i ;lÞpðc i jxÞ; (18) where pðhjO n ; c i ;lÞ is the voting probability for an object position given its category label O n , codeword c i , and locationl. The probability pðO n jc i ;lÞ denotes the confidence that the codeword is matched on the object category O n against the background.…”

Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images

“…Different CRFs may take various classifiers as unary potentials, such as boosting potential [17] and kernel CRF [15]. In this CRF, our unary potential is defined by the general logistic classifier [20], and the likelihood features are given by the MLFD.…”

Spatial-Spectral-Emissivity Land-Cover Classification Fusing Visible and Thermal Infrared Hyperspectral Imagery

“…In order to build distributions over the combined set of input variables y that are always called the observed field, and the output variables x that are the label field that we expect to predict, the probabilistic discriminative model can model the posterior probability distribution under the condition of the given observation data as a Gibbs distribution [34] with the following form:…”