Krishna Chaitanya — accepted AI-conference papers

2023

Explicitly Minimizing the Blur Error of Variational Autoencoders

Gustav Bredell, Kyriakos Flouris, Krishna Chaitanya, Ertunc Erdil, Ender Konukoglu

ICLR 2023poster

Variational autoencoders (VAEs) are powerful generative modelling methods, however they suffer from blurry generated samples and reconstructions compared to the images they have been trained on. Significant research effort has been spent to increase the generative capabilities by creating more flexi…

Cited by 30 Source ↗PDF ↗Scholar ↗

2020

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

Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu

NeurIPS 2020oral

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 (SSL) can help in this regard by providing a strategy to pre-train a neural network with unlabeled data, followed by fi…

Cited by 664 Source ↗PDF ↗code ↗Scholar ↗