activity
20162023
most citedDomain Generalization via Model-Agnostic Learning of Semantic Features

430 citations · 683 across the 11 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.CV2019430 cited

Domain Generalization via Model-Agnostic Learning of Semantic Features

Qi Dou, Daniel C. Castro, Konstantinos Kamnitsas +1

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain general…

eess.IV2019

Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation

Cheng Ouyang, Konstantinos Kamnitsas, Carlo Biffi +2

Deep learning models trained on medical images from a source domain (e.g. imaging modality) often fail when deployed on images from a different target domain, despite imaging commo…

cs.CV2019

Multiple Landmark Detection using Multi-Agent Reinforcement Learning

Athanasios Vlontzos, Amir Alansary, Konstantinos Kamnitsas +2

The detection of anatomical landmarks is a vital step for medical image analysis and applications for diagnosis, interpretation and guidance. Manual annotation of landmarks is a te…

cs.LG2019

Overfitting of neural nets under class imbalance: Analysis and improvements for segmentation

Zeju Li, Konstantinos Kamnitsas, Ben Glocker

Overfitting in deep learning has been the focus of a number of recent works, yet its exact impact on the behavior of neural networks is not well understood. This study analyzes ove…

eess.IV2019

Explainable Anatomical Shape Analysis through Deep Hierarchical Generative Models

Carlo Biffi, Juan J. Cerrolaza, Giacomo Tarroni +12

Quantification of anatomical shape changes currently relies on scalar global indexes which are largely insensitive to regional or asymmetric modifications. Accurate assessment of p…

cs.CG2019

Controlling Meshes via Curvature: Spin Transformations for Pose-Invariant Shape Processing

Loic Le Folgoc, Daniel C. Castro, Jeremy Tan +5

We investigate discrete spin transformations, a geometric framework to manipulate surface meshes by controlling mean curvature. Applications include surface fairing -- flowing a me…