4.6k citations · 6.9k across the 75 of their papers we have counts for
9 papers · 1 filter
ParaDime: A Framework for Parametric Dimensionality Reduction
Andreas Hinterreiter, Christina Humer, Bernhard Kainz +1
ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space…
Estimating Categorical Counterfactuals via Deep Twin Networks
Athanasios Vlontzos, Bernhard Kainz, Ciaran M. Gilligan-Lee
Counterfactual inference is a powerful tool, capable of solving challenging problems in high-profile sectors. To perform counterfactual inference, one requires knowledge of the und…
Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
Qingjie Meng, Daniel Rueckert, Bernhard Kainz
Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising…
Projective Latent Interventions for Understanding and Fine-tuning Classifiers
Andreas Hinterreiter, Marc Streit, Bernhard Kainz
High-dimensional latent representations learned by neural network classifiers are notoriously hard to interpret. Especially in medical applications, model developers and domain exp…
Geomstats: A Python Package for Riemannian Geometry in Machine Learning
Nina Miolane, Alice Le Brigant, Johan Mathe +16
We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear manifolds, such as hyperbolic spaces, spaces of symmetric positive definite matri…
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
Samuel Budd, Emma C Robinson, Bernhard Kainz
Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinicall…
Automatic Detection of Bowel Disease with Residual Networks
Robert Holland, Uday Patel, Phillip Lung +2
Crohn's disease, one of two inflammatory bowel diseases (IBD), affects 200,000 people in the UK alone, or roughly one in every 500. We explore the feasibility of deep learning algo…
Representation Disentanglement for Multi-task Learning with application to Fetal Ultrasound
Qingjie Meng, Nick Pawlowski, Daniel Rueckert +1
One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled i…
Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
Daniel C. Castro, Jeremy Tan, Bernhard Kainz +2
Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essenti…