Decision Forests For Computer Vision And Medical Image Analysis

By S. Fruehauf. 2016

389 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages (2015, background): “(2014) estimate the predictive uncertainty Vf→V via the heuristic of looking at the variability of the forest predictions for each point (Criminisi and Shotton, 2013).”
Efficient Non-greedy Optimization of Decision Trees (2015, methodology): “[7] A. Criminisi and J. Shotton.”
Oriented edge forests for boundary detection (2014, background): “Trees are made random through bagging and/or randomized node optimization [7], in which the binary splits at the nodes of the tree are limited to using only a random subset of features.”
Robot arm pose estimation by pixel-wise regression of joint angles (2016, background): “For a more in-depth review, we refer to [10].”
Learning 6D Object Pose Estimation Using 3D Object Coordinates (2014, methodology): “We build the decision trees using a standard randomized training procedure [2].”
Deep Neural Decision Forests (2015, methodology): “Random forests [1, 4, 7] have a rich and successful history in machine learning in general and the computer vision community in particular.”
Affordance detection of tool parts from geometric features (2015, background): “The main advantage of RFs is that inference is extremely efficient [6] , since data only needs to be passed through several binary decision functions.”
Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning (2017, methodology): “The mappings for {M} make use of a Gaussian radial basis function (RBF) network [4] as suggested by Carreira et al.”
A visual analytics approach to understanding cycling behaviour (2012, unknown): “The language bias L , through mode declarations and determination predicates, can restrict S H during hypothesis search to only allow a smaller set of candidate hypotheses H c to be searched.”
Fast and accurate image upscaling with super-resolution forests (2015, methodology): “In the next section, we detail our approach and show how random forests [2, 6, 10] can be used as an effective algorithm to learn this mapping, which has some critical benefits over previous works.”
Cascaded hand pose regression (2015, methodology): “(5) To learn Rt (line 4), we use the standard regression random forest [3, 7].”
Adaptive Neural Trees (2018, methodology): “Alternatively, DTs are characterised by learning hierarchical clusters of data (Criminisi & Shotton, 2013).”
Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information (2016, methodology): “The choice of a random forest classifier is motivated by its recent success in a variety of computer vision and medical image analysis applications where it outperformed other widely-used classifiers such as AdaBoost and support vector machines [45].”
Tree-Based Conditional Portfolio Sorts: The Relation between Past and Future Stock Returns (2016, unknown): “While early attempts in this direction focused on smaller sets of characteristics were undertaken by Haugen and Baker (1996), Daniel and Titman (1997) and Brennan et al.”
Narrowing the Gap: Random Forests In Theory and In Practice (2013, methodology): “Unlike in boosting (Schapire & Freund, 2012) where the base models are trained and combined using a sophisticated weighting scheme, typically the trees are trained independently and the predictions of the trees are combined through averaging.”