no code implementations • 1 Mar 2024 • Athanasios Tragakis, Qianying Liu, Chaitanya Kaul, Swalpa Kumar Roy, Hang Dai, Fani Deligianni, Roderick Murray-Smith, Daniele Faccio
We propose a novel transformer-style architecture called Global-Local Filter Network (GLFNet) for medical image segmentation and demonstrate its state-of-the-art performance.
no code implementations • 26 Oct 2023 • Gabriel Nobis, Marco Aversa, Maximilian Springenberg, Michael Detzel, Stefano Ermon, Shinichi Nakajima, Roderick Murray-Smith, Sebastian Lapuschkin, Christoph Knochenhauer, Luis Oala, Wojciech Samek
We generalize the continuous time framework for score-based generative models from an underlying Brownian motion (BM) to an approximation of fractional Brownian motion (FBM).
no code implementations • 28 Feb 2023 • Kevin Mitchell, Khaled Kassem, Chaitanya Kaul, Valentin Kapitany, Philip Binner, Andrew Ramsay, Roderick Murray-Smith, Daniele Faccio
For widespread adoption, public security and surveillance systems must be accurate, portable, compact, and real-time, without impeding the privacy of the individuals being observed.
1 code implementation • 4 Nov 2022 • Luis Oala, Marco Aversa, Gabriel Nobis, Kurt Willis, Yoan Neuenschwander, Michèle Buck, Christian Matek, Jerome Extermann, Enrico Pomarico, Wojciech Samek, Roderick Murray-Smith, Christoph Clausen, Bruno Sanguinetti
This limits our ability to study and understand the relationship between data generation and downstream machine learning model performance in a physically accurate manner.
1 code implementation • 14 Oct 2022 • Qianying Liu, Chaitanya Kaul, Jun Wang, Christos Anagnostopoulos, Roderick Murray-Smith, Fani Deligianni
For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture long-range correlations.
no code implementations • 26 Jul 2022 • Joshua Mitton, Simon Peter Mekhail, Miles Padgett, Daniele Faccio, Marco Aversa, Roderick Murray-Smith
We develop a new type of model for solving the task of inverting the transmission effects of multi-mode optical fibres through the construction of an $\mathrm{SO}^{+}(2, 1)$-equivariant neural network.
2 code implementations • 1 Jun 2022 • Athanasios Tragakis, Chaitanya Kaul, Roderick Murray-Smith, Dirk Husmeier
To address this shortcoming, we propose The Fully Convolutional Transformer (FCT), which builds on the proven ability of Convolutional Neural Networks to learn effective image representations, and combines them with the ability of Transformers to effectively capture long-term dependencies in its inputs.
Ranked #1 on Medical Image Segmentation on ACDC
1 code implementation • 12 May 2022 • Shameem A Puthiya Parambath, Christos Anagnostopoulos, Roderick Murray-Smith
We propose to augment the transformer-based causal language models for query recommendations to adapt to the immediate user feedback using multi-armed bandit (MAB) framework.
no code implementations • 25 Nov 2021 • Joshua Mitton, Chaitanya Kaul, Roderick Murray-Smith
Our rotation equivariant model outperforms state-of-the-art methods on a real-world dataset and we demonstrate that it accurately captures the shape and pose in the generated meshes under rotation of the input hand.
no code implementations • 23 Nov 2021 • Joshua Mitton, Roderick Murray-Smith
In this work we develop a new method, named Sub-graph Permutation Equivariant Networks (SPEN), which provides a framework for building graph neural networks that operate on sub-graphs, while using a base update function that is permutation equivariant, that are equivariant to a novel choice of automorphism group.
no code implementations • 21 Nov 2021 • Chaitanya Kaul, Joshua Mitton, Hang Dai, Roderick Murray-Smith
It achieves this feat due to its effectiveness in creating a novel and robust attention-based point set embedding through a convolutional projection layer crafted for processing dynamically local point set neighbourhoods.
no code implementations • 26 Oct 2021 • Valentin Charvet, Bjørn Sand Jensen, Roderick Murray-Smith
Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy.
Model-based Reinforcement Learning reinforcement-learning +1
2 code implementations • 25 Oct 2021 • Joshua Mitton, Roderick Murray-Smith
Deforestation has become a significant contributing factor to climate change and, due to this, both classifying the drivers and predicting segmentation maps of deforestation has attracted significant interest.
no code implementations • 7 Sep 2021 • Roderick Murray-Smith, John H. Williamson, Andrew Ramsay, Francesco Tonolini, Simon Rogers, Antoine Loriette
We infer finger 3D position $(x, y, z)$ and pose (pitch and yaw) on a mobile device using capacitive sensors which can sense the finger up to 5cm above the screen.
no code implementations • 31 Aug 2021 • Shameem A. Puthiya Parambath, Christos Anagnostopoulos, Roderick Murray-Smith, Sean MacAvaney, Evangelos Zervas
We show that such a selection strategy often results in higher cumulative regret and to this end, we propose a selection strategy based on the maximum utility of the arms.
no code implementations • 9 Aug 2021 • Sean MacAvaney, Craig Macdonald, Roderick Murray-Smith, Iadh Ounis
Existing approaches often rely on massive query logs and interaction data to generate a variety of possible query intents, which then can be used to re-rank documents.
1 code implementation • 4 Aug 2021 • Adalberto Claudio Quiros, Nicolas Coudray, Anna Yeaton, Wisuwat Sunhem, Roderick Murray-Smith, Aristotelis Tsirigos, Ke Yuan
We present an adversarial learning model to extract feature representations of cancer tissue, without the need for manual annotations.
no code implementations • 4 Jul 2021 • Marija Jegorova, Chaitanya Kaul, Charlie Mayor, Alison Q. O'Neil, Alexander Weir, Roderick Murray-Smith, Sotirios A. Tsaftaris
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data.
no code implementations • 9 Apr 2021 • Joshua Mitton, Hans M. Senn, Klaas Wynne, Roderick Murray-Smith
Finally, we demonstrate that the model is interpretable by generating molecules controlled by molecular properties, and we then analyse and visualise the learned latent representation.
no code implementations • ICLR 2021 • Francesco Tonolini, Pablo G. Moreno, Andreas Damianou, Roderick Murray-Smith
We propose a new probabilistic method for unsupervised recovery of corrupted data.
1 code implementation • 13 Apr 2020 • Adalberto Claudio Quiros, Roderick Murray-Smith, Ke Yuan
We present a deep generative model that learns to simulate high-fidelity cancer tissue images while mapping the real images onto an interpretable low dimensional latent space.
no code implementations • 4 Dec 2019 • Chaitanya Kaul, Nick Pears, Hang Dai, Roderick Murray-Smith, Suresh Manandhar
We propose a new residual block for convolutional neural networks and demonstrate its state-of-the-art performance in medical image segmentation.
no code implementations • 2 Dec 2019 • Alex Turpin, Gabriella Musarra, Valentin Kapitany, Francesco Tonolini, Ashley Lyons, Ilya Starshynov, Federica Villa, Enrico Conca, Francesco Fioranelli, Roderick Murray-Smith, Daniele Faccio
Traditional paradigms for imaging rely on the use of a spatial structure, either in the detector (pixels arrays) or in the illumination (patterned light).
no code implementations • 22 Oct 2019 • Chaitanya Kaul, Nick Pears, Hang Dai, Roderick Murray-Smith, Suresh Manandhar
Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth.
2 code implementations • 13 Sep 2019 • Hunter Gabbard, Chris Messenger, Ik Siong Heng, Francesco Tonolini, Roderick Murray-Smith
Gravitational wave (GW) detection is now commonplace and as the sensitivity of the global network of GW detectors improves, we will observe $\mathcal{O}(100)$s of transient GW events per year.
1 code implementation • MIDL 2019 • Adalberto Claudio Quiros, Roderick Murray-Smith, Ke Yuan
We show that our model generates high quality images, with a FID of 16. 65 (breast cancer) and 32. 05 (colorectal cancer).
no code implementations • ICLR 2019 • Francesco Tonolini, Bjorn Sand Jensen, Roderick Murray-Smith
We show that these sparse representations are advantageous over standard VAE representations on two benchmark classification tasks (MNIST and Fashion-MNIST) by demonstrating improved classification accuracy and significantly increased robustness to the number of latent dimensions.
no code implementations • 12 Apr 2019 • Francesco Tonolini, Jack Radford, Alex Turpin, Daniele Faccio, Roderick Murray-Smith
In such a way, Bayesian machine learning models can solve imaging inverse problems with minimal data collection efforts.
1 code implementation • NeurIPS 2018 • Oisín Moran, Piergiorgio Caramazza, Daniele Faccio, Roderick Murray-Smith
We generated experimental data based on collections of optical fibre responses to greyscale input images generated with coherent light, by measuring only image amplitude (not amplitude and phase as is typical) at the output of \SI{1}{\metre} and \SI{10}{\metre} long, \SI{105}{\micro\metre} diameter multimode fibre.
no code implementations • 21 Sep 2017 • Piergiorgio Caramazza, Alessandro Boccolini, Daniel Buschek, Matthias Hullin, Catherine Higham, Robert Henderson, Roderick Murray-Smith, Daniele Faccio
Light scattered from multiple surfaces can be used to retrieve information of hidden environments.