activity
20182022
most citedA Field of Experts Prior for Adapting Neural Networks at Test Time

1 citations · 1 across the 1 of their papers we have counts for

collaborators

8 papers

cs.CV20221 cited

A Field of Experts Prior for Adapting Neural Networks at Test Time

Neerav Karani, Georg Brunner, Ertunc Erdil +4

Performance of convolutional neural networks (CNNs) in image analysis tasks is often marred in the presence of acquisition-related distribution shifts between training and test ima…

eess.IV2020

Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE

Anna Volokitin, Ertunc Erdil, Neerav Karani +4

Probabilistic modelling has been an essential tool in medical image analysis, especially for analyzing brain Magnetic Resonance Images (MRI). Recent deep learning techniques for es…

eess.IV2020

Semi-supervised Task-driven Data Augmentation for Medical Image Segmentation

Krishna Chaitanya, Neerav Karani, Christian F. Baumgartner +4

Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such d…

cs.CV2020

Contrastive learning of global and local features for medical image segmentation with limited annotations

Krishna Chaitanya, Ertunc Erdil, Neerav Karani +1

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning…

eess.IV2020

Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation

Neerav Karani, Ertunc Erdil, Krishna Chaitanya +1

Convolutional Neural Networks (CNNs) work very well for supervised learning problems when the training dataset is representative of the variations expected to be encountered at tes…

cs.CV2019

Semi-Supervised and Task-Driven Data Augmentation

Krishna Chaitanya, Neerav Karani, Christian Baumgartner +3

Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen imag…