no code implementations • 11 Mar 2024 • Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Contrastive instance discrimination outperforms supervised learning in downstream tasks like image classification and object detection.
no code implementations • 7 Mar 2024 • Miles Everett, Mingjun Zhong, Georgios Leontidis
We propose Masked Capsule Autoencoders (MCAE), the first Capsule Network that utilises pretraining in a self-supervised manner.
no code implementations • 19 Jul 2023 • Miles Everett, Mingjun Zhong, Georgios Leontidis
Our findings underscore the potential of our proposed methodology in enhancing the operational efficiency and performance of Capsule Networks, paving the way for their application in increasingly complex computational scenarios.
no code implementations • 17 Jul 2023 • Rebecca Potts, Rick Hackney, Georgios Leontidis
Predicting emissions for gas turbines is critical for monitoring harmful pollutants being released into the atmosphere.
no code implementations • 28 Jun 2023 • Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks.
no code implementations • 19 May 2023 • Alžběta Manová, Aiden Durrant, Georgios Leontidis
In this work, we aim to learn highly separable semantic hierarchical representations by stacking Joint Embedding Architectures (JEA) where higher-level JEAs are input with representations of lower-level JEA.
no code implementations • 18 May 2023 • Aiden Durrant, Georgios Leontidis
Hyperbolic manifolds for visual representation learning allow for effective learning of semantic class hierarchies by naturally embedding tree-like structures with low distortion within a low-dimensional representation space.
no code implementations • 13 May 2023 • Miles Everett, Mingjun Zhong, Georgios Leontidis
This paper extends the investigation to a range of leading Capsule Network architectures, demonstrating that these issues are not confined to the original design.
no code implementations • 19 Apr 2023 • Andy Li, Milan Markovic, Peter Edwards, Georgios Leontidis
Federated Learning (FL) presents a decentralized approach to model training in the agri-food sector and offers the potential for improved machine learning performance, while ensuring the safety and privacy of individual farms or data silos.
no code implementations • 16 Apr 2023 • Iraklis Giannakis, Anshuman Bhardwaj, Lydia Sam, Georgios Leontidis
Existing ML approaches for automated crater detection have been trained in specific types of data e. g. digital elevation model (DEM), images and associated metadata for orbiters such as the Lunar Reconnaissance Orbiter Camera (LROC) etc.. Due to that, each of the resulting ML schemes is applicable and reliable only to the type of data used during the training process.
no code implementations • 15 Nov 2022 • George Onoufriou, Marc Hanheide, Georgios Leontidis
Yield forecasting is a critical first step necessary for yield optimisation, with important consequences for the broader food supply chain, procurement, price-negotiation, logistics, and supply.
no code implementations • 12 Nov 2022 • Mamatha Thota, Dewei Yi, Georgios Leontidis
Humans and animals have the ability to continuously learn new information over their lifetime without losing previously acquired knowledge.
no code implementations • 6 Jun 2022 • Fabio De Sousa Ribeiro, Kevin Duarte, Miles Everett, Georgios Leontidis, Mubarak Shah
The aim of this survey is to provide a comprehensive overview of the capsule network research landscape, which will serve as a valuable resource for the community going forward.
no code implementations • 26 Oct 2021 • George Onoufriou, Marc Hanheide, Georgios Leontidis
We present automatically parameterised Fully Homomorphic Encryption (FHE) for encrypted neural network inference and exemplify our inference over FHE compatible neural networks with our own open-source framework and reproducible examples.
1 code implementation • 26 Jul 2021 • George Onoufriou, Paul Mayfield, Georgios Leontidis
Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of privacy-preserving technologies.
no code implementations • 29 Apr 2021 • Aiden Durrant, Georgios Leontidis
Bootstrap Your Own Latent (BYOL) introduced an approach to self-supervised learning avoiding the contrastive paradigm and subsequently removing the computational burden of negative sampling associated with such methods.
no code implementations • 14 Apr 2021 • Aiden Durrant, Milan Markovic, David Matthews, David May, Jessica Enright, Georgios Leontidis
Data sharing remains a major hindering factor when it comes to adopting emerging AI technologies in general, but particularly in the agri-food sector.
no code implementations • 26 Mar 2021 • Mamatha Thota, Georgios Leontidis
Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks.
no code implementations • 7 Dec 2020 • Bashar Alhnaity, Stefanos Kollias, Georgios Leontidis, Shouyong Jiang, Bert Schamp, Simon Pearson
Finally, a recurrent neural network including LSTM and an attention mechanism is proposed for modelling long-term dependencies in the time series data.
no code implementations • NeurIPS 2020 • Fabio De Sousa Ribeiro, Georgios Leontidis, Stefanos Kollias
Rather than performing inefficient local iterative routing between adjacent capsule layers, we propose an alternative global view based on representing the inherent uncertainty in part-object assignment.
no code implementations • 15 Jun 2020 • Wei Wei, Bei Zhou, Georgios Leontidis
This paper proposes an enhanced natural language generation system combining the merits of both rule-based approaches and modern deep learning algorithms, boosting its performance to the extent where the generated textual content is capable of exhibiting agile human-writing styles and the content logic of which is highly controllable.
no code implementations • 30 Mar 2020 • Benedict Delahaye Chivers, John Wallbank, Steven J. Cole, Ondrej Sebek, Simon Stanley, Matthew Fry, Georgios Leontidis
Precipitation data collected at sub-hourly resolution represents specific challenges for missing data recovery by being largely stochastic in nature and highly unbalanced in the duration of rain vs non-rain.
no code implementations • 28 Jan 2020 • Mamatha Thota, Stefanos Kollias, Mark Swainson, Georgios Leontidis
The presence and accuracy of such information is critical to ensure a detailed understanding of the product and to reduce the potential for health risks.
no code implementations • 1 Jul 2019 • Bashar Alhnaity, Simon Pearson, Georgios Leontidis, Stefanos Kollias
Effective plant growth and yield prediction is an essential task for greenhouse growers and for agriculture in general.
1 code implementation • 4 Jun 2019 • George Onoufriou, Ronald Bickerton, Simon Pearson, Georgios Leontidis
Deep Learning has attracted considerable attention across multiple application domains, including computer vision, signal processing and natural language processing.
1 code implementation • 27 May 2019 • Fabio De Sousa Ribeiro, Georgios Leontidis, Stefanos Kollias
Capsule networks are a recently proposed type of neural network shown to outperform alternatives in challenging shape recognition tasks.
Ranked #3 on Image Classification on smallNORB
1 code implementation • 26 Nov 2018 • Fabio De Sousa Ribeiro, Francesco Caliva, Mark Swainson, Kjartan Gudmundsson, Georgios Leontidis, Stefanos Kollias
Supervised Deep Learning has been highly successful in recent years, achieving state-of-the-art results in most tasks.
no code implementations • 26 Jul 2018 • Fabio De Sousa Ribeiro, Francesco Caliva, Dionysios Chionis, Abdelhamid Dokhane, Antonios Mylonakis, Christophe Demaziere, Georgios Leontidis, Stefanos Kollias
512 dimensional representations were extracted from the 3D-CNN and LSTM architectures, and used as input to a fused multi-sigmoid classification layer to recognise the perturbation type.