Image Modeling Using Tree Structured Conditional Random Fields
نویسندگان
چکیده
In this paper we present a discriminative framework based on conditional random fields for stochastic modeling of images in a hierarchical fashion. The main advantage of the proposed framework is its ability to incorporate a rich set of interactions among the image sites. We achieve this by inducing a hierarchy of hidden variables over the given label field. The proposed tree like structure of our model eliminates the need for a huge parameter space and at the same time permits the use of exact and efficient inference procedures based on belief propagation. We demonstrate the generality of our approach by applying it to two important computer vision tasks, namely image labeling and object detection. The model parameters are trained using the contrastive divergence algorithm. We report the performance on real world images and compare it with the existing approaches.
منابع مشابه
Conditional Random Fields for Pattern Recognition Applied to Structured Data
Pattern recognition uses measurements from an input domain, X, to predict their labels from an output domain, Y. Image analysis is one setting where one might want to infer whether a pixel patch contains an object that is “manmade” (such as a building) or “natural” (such as a tree). Suppose the label for a pixel patch is “manmade”; if the label for a nearby pixel patch is then more likely to be...
متن کاملWord Sense Disambiguation for All Words using Tree-Structured Conditional Random Fields
We propose a supervised word sense disambiguation (WSD) method using tree-structured conditional random fields (TCRFs). By applying TCRFs to a sentence described as a dependency tree structure, we conduct WSD as a labeling problem on tree structures. To incorporate dependencies between word senses, we introduce a set of features on tree edges, in combination with coarse-grained tagsets, and sho...
متن کاملTree-Structured Like Representations for Continuous and Discrete Indexed Markov Random Fields
Markov random fields (MRFs) are ubiquitous models for conveniently capturing complex statistical dependencies given a collection of random variables. For example, when modeling the temperature distribution of a continuously indexed region, it is common to assume that the temperature at one point depends on some differential neighborhood. MRFs can capture such dependencies using a set of conditi...
متن کاملEfficient Structured Prediction with Latent Variables for General Graphical Models
In this paper we propose a unified framework for structured prediction with latent variables which includes hidden conditional random fields and latent structured support vector machines as special cases. We describe a local entropy approximation for this general formulation using duality, and derive an efficient message passing algorithm that is guaranteed to converge. We demonstrate its effec...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007