Search Results for author: Boguslaw Obara

Found 14 papers, 7 papers with code

Not Half Bad: Exploring Half-Precision in Graph Convolutional Neural Networks

no code implementations23 Oct 2020 John Brennan, Stephen Bonner, Amir Atapour-Abarghouei, Philip T Jackson, Boguslaw Obara, Andrew Stephen McGough

With the growing significance of graphs as an effective representation of data in numerous applications, efficient graph analysis using modern machine learning is receiving a growing level of attention.

Link Prediction

Camera Bias in a Fine Grained Classification Task

no code implementations16 Jul 2020 Philip T. Jackson, Stephen Bonner, Ning Jia, Christopher Holder, Jon Stonehouse, Boguslaw Obara

We show that correlations between the camera used to acquire an image and the class label of that image can be exploited by convolutional neural networks (CNN), resulting in a model that "cheats" at an image classification task by recognizing which camera took the image and inferring the class label from the camera.

Classification General Classification +1

Segmentation of Macular Edema Datasets with Small Residual 3D U-Net Architectures

no code implementations10 May 2020 Jonathan Frawley, Chris G. Willcocks, Maged Habib, Caspar Geenen, David H. Steel, Boguslaw Obara

This paper investigates the application of deep convolutional neural networks with prohibitively small datasets to the problem of macular edema segmentation.

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions

1 code implementation21 Aug 2019 Stephen Bonner, Amir Atapour-Abarghouei, Philip T. Jackson, John Brennan, Ibad Kureshi, Georgios Theodoropoulos, Andrew Stephen McGough, Boguslaw Obara

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines.

Social and Information Networks

TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text

1 code implementation28 Apr 2019 Fady Medhat, Mahnaz Mohammadi, Sardar Jaf, Chris G. Willcocks, Toby P. Breckon, Peter Matthews, Andrew Stephen McGough, Georgios Theodoropoulos, Boguslaw Obara

In this work, we present a generic process flow for text recognition in scanned documents containing mixed handwritten and machine-printed text without the need to classify text in advance.

Phenotypic Profiling of High Throughput Imaging Screens with Generic Deep Convolutional Features

no code implementations15 Mar 2019 Philip T. Jackson, Yinhai Wang, Sinead Knight, Hongming Chen, Thierry Dorval, Martin Brown, Claus Bendtsen, Boguslaw Obara

While deep learning has seen many recent applications to drug discovery, most have focused on predicting activity or toxicity directly from chemical structure.

Clustering Drug Discovery

2D and 3D Vascular Structures Enhancement via Multiscale Fractional Anisotropy Tensor

1 code implementation1 Feb 2019 Haifa F. Alhasson, Shuaa S. Alharbi, Boguslaw Obara

The detection of vascular structures from noisy images is a fundamental process for extracting meaningful information in many applications.

Curvilinear Structure Enhancement by Multiscale Top-Hat Tensor in 2D/3D Images

1 code implementation23 Sep 2018 Shuaa S. Alharbi, Cigdem Sazak, Carl J. Nelson, Boguslaw Obara

The proposed approach is validated on synthetic and real data and is also compared to the state-of-the-art approaches.

Style Augmentation: Data Augmentation via Style Randomization

1 code implementation14 Sep 2018 Philip T. Jackson, Amir Atapour-Abarghouei, Stephen Bonner, Toby Breckon, Boguslaw Obara

In addition to standard classification experiments, we investigate the effect of style augmentation (and data augmentation generally) on domain transfer tasks.

Classification Data Augmentation +4

Exploring the Semantic Content of Unsupervised Graph Embeddings: An Empirical Study

2 code implementations19 Jun 2018 Stephen Bonner, Ibad Kureshi, John Brennan, Georgios Theodoropoulos, Andrew Stephen McGough, Boguslaw Obara

To explore this, we present extensive experimental evaluation from five state-of-the-art unsupervised graph embedding techniques, across a range of empirical graph datasets, measuring a selection of topological features.

Graph Embedding Graph Mining

The Multiscale Bowler-Hat Transform for Vessel Enhancement in 3D Biomedical Images

no code implementations14 Feb 2018 Cigdem Sazak, Carl J. Nelson, Boguslaw Obara

Enhancement and detection of 3D vessel-like structures has long been an open problem as most existing image processing methods fail in many aspects, including a lack of uniform enhancement between vessels of different radii and a lack of enhancement at the junctions.

The Multiscale Bowler-Hat Transform for Blood Vessel Enhancement in Retinal Images

no code implementations16 Sep 2017 Çiğdem Sazak, Carl J. Nelson, Boguslaw Obara

Enhancement, followed by segmentation, quantification and modelling, of blood vessels in retinal images plays an essential role in computer-aid retinopathy diagnosis.

Cannot find the paper you are looking for? You can Submit a new open access paper.