Decision tree fields

By Sebastian Nowozin, Carsten Rother, Shai Bagon, Toby Sharp, Bangpeng Yao, Pushmeet Kohli. 2011

130 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Ocean Engineering

In Natural Language Processing

Citations in the corpus

Barrier Frank-Wolfe for Marginal Inference (2015, methodology): “The potentials were learned using Decision Tree Fields (Nowozin et al., 2011).”
Learning Deep Structured Models (2014, background): “More recently, several attempts have been presented to extend conditional random fields to learn non-linear functions.”
A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources (2019, unknown): “Decision tree fields [99] Combination of random forests and random fields.”
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems (2014, methodology): “We also consider the task of inpainting in binary images of Chinese characters, dtf-chinesechar [61].”
Contextual classification of lidar data and building object detection in urban areas (2014, methodology): “Going beyond our previous work, the pairwise potentials are based on RF, but unlike in Nowozin et al. (2011), our graph is based on points and, thus, irregular.”
Joint Training of Generic CNN-CRF Models with Stochastic Optimization (2015, methodology): “One example is the Decision Tree Field approach [4] where factors are dependent on Decision Trees.”
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, background): “A related line of work [13, 18, 21, 23] proposes decision forests methods for image segmentation.”
Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2012, methodology): “Recent years have seen an explosion of forest-based techniques in the machine learning, vision and medical imaging literature [9, 15, 25, 31, 35, 37, 58, 59, 65, 67, 68, 69, 74, 79, 89, 92, 97, 110].”
Superparsing (2010, background): “…Bayes assumption that features are independent of each other given the class, the likelihood ratio for class c and superpixel si is L(si, c) = P (si|c) P (si|c̄) = ∏ k P (fki |c) P (fki |c̄) , (1) where c̄ is the set of all classes excluding c, and fki is the feature vector of the kth type for si.”
Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2011, methodology): “the machine learning, vision and medical imaging literature [9, 15, 24, 29, 33, 35, 52, 53, 54, 56, 58, 59, 60, 61, 65, 70, 80, 83, 88, 102].”
Conditional regression forests for human pose estimation (2012, unknown): “They have been successfully applied to problems such as image classification [16], object detection and segmentation [10, 22], human pose estimation [12, 29], action recognition [10], and even image completion [24].”
Closed-Form Approximate CRF Training for Scalable Image Segmentation (2014, background): “To our knowledge this feature is only shared by decision tree fields (DTFs) [25], which differ, however, in other aspects.”
Unrolling Loopy Top-Down Semantic Feedback in Convolutional Deep Networks (2014, background): “Some recent proposals aim at fully learnable contextual interaction [21, 26, 3].”
Human Pose Estimation with Fields of Parts (2014, methodology): “The decision tree implementation of [21] and its features are used to train a person/background classifier on the training images.”
Efficient Likelihood Learning of a Generic CNN-CRF Model for Semantic Segmentation (2015, background): “Note however, that again a model approximation takes place here, since Mean Field is an approximation of the maximum marginal decision indeed.”