Proceedings Article10.1109/ICCV.2011.6126429
Decision tree fields
Sebastian Nowozin,Carsten Rother,Shai Bagon,Toby Sharp,Bangpeng Yao,Pushmeet Kohli +5 more
- 06 Nov 2011
- pp 1668-1675
TL;DR: This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields which have been widely used in computer vision.
read more
Abstract: This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from sophisticated random forest or boosting based classifiers, however, the pairwise potentials are assumed to (1) have a simple parametric form with a pre-specified and fixed dependence on the image data, and (2) to be defined on the basis of a small and fixed neighborhood. In contrast, in DTF, local interactions between multiple variables are determined by means of decision trees evaluated on the image data, allowing the interactions to be adapted to the image content. This results in powerful graphical models which are able to represent complex label structure. Our key technical contribution is to show that the DTF model can be trained efficiently and jointly using a convex approximate likelihood function, enabling us to learn over a million free model parameters. We show experimentally that for applications which have a rich and complex label structure, our model achieves excellent results.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Book
Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold, Learning and Semi-supervised Learning
Antonio Criminisi,Jamie Shotton,Ender Konukoglu +2 more
- 14 Mar 2012
TL;DR: A unified, efficient model of random decision forests which can be applied to a number of machine learning, computer vision, and medical image analysis tasks is presented and relative advantages and disadvantages discussed.
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Guosheng Lin,Chunhua Shen,Anton van den Hengel,Ian Reid +3 more
- 27 Jun 2016
TL;DR: Zhang et al. as discussed by the authors proposed a patch-patch context between image regions and patch-background context, and formulated conditional random fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches.
Superparsing: scalable nonparametric image parsing with superpixels
Joseph Tighe,Svetlana Lazebnik +1 more
- 05 Sep 2010
TL;DR: This paper presents a simple and effective nonparametric approach to the problem of image parsing, or labeling image regions (in this case, superpixels produced by bottom-up segmentation) with their categories, and establishes a new benchmark for the problem.
Decision Forests for Computer Vision and Medical Image Analysis
Antonio Criminisi,Jamie Shotton +1 more
- 31 Jan 2013
TL;DR: This practical and easy-to-follow text explores the theoretical underpinnings of decision forests, organizing the vast existing literature on the field within a new, general-purpose forest model.
677
Contextual classification of lidar data and building object detection in urban areas
TL;DR: This work integrates a Random Forest classifier into a Conditional Random Field framework, a flexible approach for obtaining a reliable classification result even in complex urban scenes, and investigates the relevance of different features for the LiDAR points as well as for the interaction of neighbouring points.
577
References
Random Forests
Leo Breiman
- 01 Oct 2001
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
Stuart Geman,Donald Geman +1 more
TL;DR: The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
•Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
John Lafferty,Andrew McCallum,Fernando Pereira +2 more
- 28 Jun 2001
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
•Book
Probabilistic graphical models : principles and techniques
Daniel L. Koller,Nir Friedman +1 more
- 31 Jul 2009
TL;DR: The framework of probabilistic graphical models, presented in this book, provides a general approach for causal reasoning and decision making under uncertainty, allowing interpretable models to be constructed and then manipulated by reasoning algorithms.