1 code implementation • 18 Sep 2024 • Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
This study introduces unORANIC+, a novel method that integrates unsupervised feature orthogonalization with the ability of a Vision Transformer to capture both local and global relationships for improved robustness and generalizability.
1 code implementation • 26 Aug 2024 • Francesco Di Salvo, Sebastian Doerrich, Ines Rieger, Christian Ledig
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems.
1 code implementation • 1 Aug 2024 • Francesco Di Salvo, David Tafler, Sebastian Doerrich, Christian Ledig
Large and well-annotated datasets are essential for advancing deep learning applications, however often costly or impossible to obtain by a single entity.
1 code implementation • 3 Jul 2024 • Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
To this end, we propose a novel generative method for domain generalization in histopathology images.
1 code implementation • 25 Jun 2024 • Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness.
1 code implementation • 24 Apr 2024 • Sebastian Doerrich, Francesco Di Salvo, Julius Brockmann, Christian Ledig
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets.
1 code implementation • 19 Feb 2024 • Sebastian Doerrich, Tobias Archut, Francesco Di Salvo, Christian Ledig
Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes.
1 code implementation • 29 Aug 2023 • Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
We introduce unORANIC, an unsupervised approach that uses an adapted loss function to drive the orthogonalization of anatomy and image-characteristic features.
1 code implementation • 28 Jun 2019 • Carlo Biffi, Juan J. Cerrolaza, Giacomo Tarroni, Wenjia Bai, Antonio de Marvao, Ozan Oktay, Christian Ledig, Loic Le Folgoc, Konstantinos Kamnitsas, Georgia Doumou, Jinming Duan, Sanjay K. Prasad, Stuart A. Cook, Declan P. O'Regan, Daniel Rueckert
At the highest level of this hierarchy, a two-dimensional latent space is simultaneously optimised to discriminate distinct clinical conditions, enabling the direct visualisation of the classification space.
no code implementations • 6 Feb 2019 • Anant Gupta, Srivas Venkatesh, Sumit Chopra, Christian Ledig
Insufficient training data and severe class imbalance are often limiting factors when developing machine learning models for the classification of rare diseases.
no code implementations • 24 Oct 2018 • Jelmer M. Wolterink, Konstantinos Kamnitsas, Christian Ledig, Ivana Išgum
Generative adversarial networks (GANs) and other adversarial methods are based on a game-theoretical perspective on joint optimization of two neural networks as players in a game.
no code implementations • 21 Aug 2017 • Martin Rajchl, Lisa M. Koch, Christian Ledig, Jonathan Passerat-Palmbach, Kazunari Misawa, Kensaku MORI, Daniel Rueckert
To efficiently establish training databases for machine learning methods, collaborative and crowdsourcing platforms have been investigated to collectively tackle the annotation effort.
3 code implementations • 10 Jul 2017 • Andrew Aitken, Christian Ledig, Lucas Theis, Jose Caballero, Zehan Wang, Wenzhe Shi
Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernels, it is free from checkerboard artifacts immediately after initialization.
1 code implementation • 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.
no code implementations • CVPR 2017 • Jose Caballero, Christian Ledig, Andrew Aitken, Alejandro Acosta, Johannes Totz, Zehan Wang, Wenzhe Shi
Convolutional neural networks have enabled accurate image super-resolution in real-time.
Ranked #11 on
Video Super-Resolution
on MSU Video Upscalers: Quality Enhancement
(VMAF metric)
6 code implementations • 22 Sep 2016 • Wenzhe Shi, Jose Caballero, Lucas Theis, Ferenc Huszar, Andrew Aitken, Christian Ledig, Zehan Wang
In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented.
140 code implementations • CVPR 2017 • Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, Wenzhe Shi
The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
Ranked #3 on
Image Super-Resolution
on VggFace2 - 8x upscaling
2 code implementations • 18 Mar 2016 • Konstantinos Kamnitsas, Christian Ledig, Virginia F. J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Daniel Rueckert, Ben Glocker
We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation.
Ranked #1 on
Lesion Segmentation
on ISLES-2015
3D Medical Imaging Segmentation
Brain Lesion Segmentation From Mri
+3
no code implementations • CVPR 2014 • Christian Ledig, Wenzhe Shi, Wenjia Bai, Daniel Rueckert
The ideal similarity measure should be unbiased to segmentations of different volume and complexity, and be able to quantify and visualise segmentation bias.