no code implementations • 31 Jul 2019 • Ryutaro Tanno, Daniel Worrall, Enrico Kaden, Aurobrata Ghosh, Francesco Grussu, Alberto Bizzi, Stamatios N. Sotiropoulos, Antonio Criminisi, Daniel C. Alexander
Here we introduce methods to characterise different components of uncertainty in such problems and demonstrate the ideas using diffusion MRI super-resolution.
In this paper, we propose to use both types of training data (fully-annotated and weakly-annotated) to train a deep learning model for segmentation.
Furthermore, we propose a network architecture in which the different MR sequences are processed by separate subnetworks in order to be more robust to the problem of missing MR sequences.
Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures.
We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation.
We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing.
Ranked #5 on Brain Tumor Segmentation on BRATS-2015
In this work, we investigate the value of uncertainty modeling in 3D super-resolution with convolutional neural networks (CNNs).
no code implementations • 28 Dec 2016 • Konstantinos Kamnitsas, Christian Baumgartner, Christian Ledig, Virginia F. J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Aditya Nori, Antonio Criminisi, Daniel Rueckert, Ben Glocker
In this work we investigate unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more invariant to differences in the input data, and which does not require any annotations on the test domain.
We consider the task of predicting various traits of a person given an image of their face.
Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled.
We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root.
Deep Convolutional Neural Networks (CNNs) have recently evinced immense success for various image recognition tasks.
We present a systematic analysis of how to fuse conditional computation with representation learning and achieve a continuum of hybrid models with different ratios of accuracy vs. efficiency.
We present Deep Neural Decision Forests - a novel approach that unifies classification trees with the representation learning functionality known from deep convolutional networks, by training them in an end-to-end manner.
Applying our method to a near state-of-the-art network for CIFAR, we achieved comparable accuracy with 46% less compute and 55% fewer parameters.
We propose 'filter forests' (FF), an efficient new discriminative approach for predicting continuous variables given a signal and its context.
Randomized decision trees and forests have a rich history in machine learning and have seen considerable success in application, perhaps particularly so for computer vision.
This paper presents a new and efficient forest based model that achieves spatially consistent semantic image segmentation by encoding variable dependencies directly in the feature space the forests operate on.
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image.
In this paper we introduce Context-Sensitive Decision Forests - A new perspective to exploit contextual information in the popular decision forest framework for the object detection problem.