4 citations · 13 across the 12 of their papers we have counts for
13 papers
Group Distributionally Robust Knowledge Distillation
Konstantinos Vilouras, Xiao Liu, Pedro Sanchez +2
Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-populat…
Compositional Representation Learning for Brain Tumour Segmentation
Xiao Liu, Antanas Kascenas, Hannah Watson +2
For brain tumour segmentation, deep learning models can achieve human expert-level performance given a large amount of data and pixel-level annotations. However, the expensive exer…
Compositionally Equivariant Representation Learning
Xiao Liu, Pedro Sanchez, Spyridon Thermos +2
Deep learning models often need sufficient supervision (i.e. labelled data) in order to be trained effectively. By contrast, humans can swiftly learn to identify important anatomy…
Diffusion Models for Causal Discovery via Topological Ordering
Pedro Sanchez, Xiao Liu, Alison Q O'Neil +1
Discovering causal relations from observational data becomes possible with additional assumptions such as considering the functional relations to be constrained as nonlinear with a…
HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information
Xiao Liu, Spyridon Thermos, Pedro Sanchez +2
Learning disentangled representations requires either supervision or the introduction of specific model designs and learning constraints as biases. InfoGAN is a popular disentangle…
What is Healthy? Generative Counterfactual Diffusion for Lesion Localization
Pedro Sanchez, Antanas Kascenas, Xiao Liu +2
Reducing the requirement for densely annotated masks in medical image segmentation is important due to cost constraints. In this paper, we consider the problem of inferring pixel-l…
Why patient data cannot be easily forgotten?
Ruolin Su, Xiao Liu, Sotirios A. Tsaftaris
Rights provisioned within data protection regulations, permit patients to request that knowledge about their information be eliminated by data holders. With the advent of AI learne…
vMFNet: Compositionality Meets Domain-generalised Segmentation
Xiao Liu, Spyridon Thermos, Pedro Sanchez +2
Training medical image segmentation models usually requires a large amount of labeled data. By contrast, humans can quickly learn to accurately recognise anatomy of interest from m…
Controllable cardiac synthesis via disentangled anatomy arithmetic
Spyridon Thermos, Xiao Liu, Alison O'Neil +1
Acquiring annotated data at scale with rare diseases or conditions remains a challenge. It would be extremely useful to have a method that controllably synthesizes images that can…
Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation
Xiao Liu, Spyridon Thermos, Alison O'Neil +1
Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between sou…
Disentangled Representations for Domain-generalized Cardiac Segmentation
Xiao Liu, Spyridon Thermos, Agisilaos Chartsias +2
Robust cardiac image segmentation is still an open challenge due to the inability of the existing methods to achieve satisfactory performance on unseen data of different domains. S…
Have you forgotten? A method to assess if machine learning models have forgotten data
Xiao Liu, Sotirios A Tsaftaris
In the era of deep learning, aggregation of data from several sources is a common approach to ensuring data diversity. Let us consider a scenario where several providers contribute…
CerfGAN: A Compact, Effective, Robust, and Fast Model for Unsupervised Multi-Domain Image-to-Image Translation
Xiao Liu, Shengchuan Zhang, Hong Liu +3
In this paper, we aim at solving the multi-domain image-to-image translation problem with a unified model in an unsupervised manner. The most successful work in this area refers to…