Search Results for author: Amir Atapour-Abarghouei

Found 28 papers, 21 papers with code

HINT: High-quality INPainting Transformer with Mask-Aware Encoding and Enhanced Attention

1 code implementation22 Feb 2024 Shuang Chen, Amir Atapour-Abarghouei, Hubert P. H. Shum

In this paper, we propose an end-to-end High-quality INpainting Transformer, abbreviated as HINT, which consists of a novel mask-aware pixel-shuffle downsampling module (MPD) to preserve the visible information extracted from the corrupted image while maintaining the integrity of the information available for high-level inferences made within the model.

Image Inpainting speech-recognition +1

INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network

no code implementations17 May 2023 Shuang Chen, Amir Atapour-Abarghouei, Edmond S. L. Ho, Hubert P. H. Shum

We present a software that predicts non-cleft facial images for patients with cleft lip, thereby facilitating the understanding, awareness and discussion of cleft lip surgeries.

Image Inpainting

Predicting the Performance of a Computing System with Deep Networks

no code implementations27 Feb 2023 Mehmet Cengiz, Matthew Forshaw, Amir Atapour-Abarghouei, Andrew Stephen McGough

Existing approaches to understanding the performance of hardware largely focus around benchmarking -- leveraging standardised workloads which seek to be representative of an end-user's needs.

Benchmarking

Siamese Neural Networks for Skin Cancer Classification and New Class Detection using Clinical and Dermoscopic Image Datasets

no code implementations12 Dec 2022 Michael Luke Battle, Amir Atapour-Abarghouei, Andrew Stephen McGough

Instead, we evaluate Siamese Neural Networks (SNNs), which not only allows us to classify images of skin lesions, but also allow us to identify those images which are different from the trained classes - allowing us to determine that an image is not an example of our training classes.

Skin Cancer Classification

Long-term Reproducibility for Neural Architecture Search

1 code implementation11 Jul 2022 David Towers, Matthew Forshaw, Amir Atapour-Abarghouei, Andrew Stephen McGough

It is a sad reflection of modern academia that code is often ignored after publication -- there is no academic 'kudos' for bug fixes / maintenance.

Neural Architecture Search

Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification

2 code implementations6 Feb 2022 Peter J. Bevan, Amir Atapour-Abarghouei

Convolutional Neural Networks have demonstrated human-level performance in the classification of melanoma and other skin lesions, but evident performance disparities between differing skin tones should be addressed before widespread deployment.

Lesion Classification Skin Lesion Classification

"Just Drive": Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving

1 code implementation2 Dec 2021 Jack Stelling, Amir Atapour-Abarghouei

However, the strategy has never been applied to the safety-critical domain of pixel-wise semantic segmentation of highly variable training data - such as urban scenes.

Segmentation Self-Driving Cars +1

Transforming Fake News: Robust Generalisable News Classification Using Transformers

1 code implementation20 Sep 2021 Ciara Blackledge, Amir Atapour-Abarghouei

Experiments over the ISOT and Combined Corpus datasets show that transformers achieve an increase in F1 scores of up to 4. 9% for out of distribution generalisation compared to baseline approaches, with a further increase of 10. 1% following the implementation of our two-step classification pipeline.

Binary Classification Classification +1

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

1 code implementation20 Sep 2021 Peter J. Bevan, Amir Atapour-Abarghouei

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible.

Skin Cancer Classification

Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking

1 code implementation5 Sep 2021 Steven Carrell, Amir Atapour-Abarghouei

The use of mobiles phones when driving have been a major factor when it comes to road traffic incidents and the process of capturing such violations can be a laborious task.

Object object-detection +2

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

Rank over Class: The Untapped Potential of Ranking in Natural Language Processing

1 code implementation10 Sep 2020 Amir Atapour-Abarghouei, Stephen Bonner, Andrew Stephen McGough

Text classification has long been a staple within Natural Language Processing (NLP) with applications spanning across diverse areas such as sentiment analysis, recommender systems and spam detection.

General Classification Information Retrieval +5

On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures

no code implementations28 Jul 2020 Matt Poyser, Amir Atapour-Abarghouei, Toby P. Breckon

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks.

Action Recognition Image Compression +7

Leveraging Synthetic Subject Invariant EEG Signals for Zero Calibration BCI

1 code implementation16 Jul 2020 Nik Khadijah Nik Aznan, Amir Atapour-Abarghouei, Stephen Bonner, Jason D. Connolly, Toby P. Breckon

Our approach, entitled the Subject Invariant SSVEP Generative Adversarial Network (SIS-GAN), produces synthetic EEG data from multiple SSVEP classes using a single network.

Signal Processing Image and Video Processing

Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor Environments

no code implementations11 Dec 2019 Bruna G. Maciel-Pearson, Letizia Marchegiani, Samet Akcay, Amir Atapour-Abarghouei, James Garforth, Toby P. Breckon

With the rapidly growing expansion in the use of UAVs, the ability to autonomously navigate in varying environments and weather conditions remains a highly desirable but as-of-yet unsolved challenge.

Navigate reinforcement-learning +1

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

A Kings Ransom for Encryption: Ransomware Classification using Augmented One-Shot Learning and Bayesian Approximation

1 code implementation19 Aug 2019 Amir Atapour-Abarghouei, Stephen Bonner, Andrew Stephen McGough

In this paper, we investigate the possibility of classifying the ransomware a system is infected with simply based on a screenshot of the splash screen or the ransom note captured using a consumer camera commonly found in any modern mobile device.

Data Augmentation General Classification +1

To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation

no code implementations15 Aug 2019 Amir Atapour-Abarghouei, Toby P. Breckon

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation.

Autonomous Driving Depth Completion +3

Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection

2 code implementations25 Jan 2019 Samet Akçay, Amir Atapour-Abarghouei, Toby P. Breckon

By contrast, we introduce an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain and hence detect abnormality based on deviation from this model.

Scene Understanding Unsupervised Anomaly Detection

Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification

1 code implementation15 Jan 2019 Nik Khadijah Nik Aznan, Amir Atapour-Abarghouei, Stephen Bonner, Jason Connolly, Noura Al Moubayed, Toby Breckon

Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments.

Quantitative Methods Signal Processing

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

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

9 code implementations17 May 2018 Samet Akcay, Amir Atapour-Abarghouei, Toby P. Breckon

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal).

Generative Adversarial Network Semi-supervised Anomaly Detection +1

DepthComp: real-time depth image completion based on prior semantic scene segmentation

1 code implementation4 Sep 2017 Amir Atapour-Abarghouei, Toby P Breckon

We address plausible hole filling in depth images in a computationally lightweight methodology that leverages recent advances in semantic scene segmentation.

Scene Segmentation Segmentation

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