794 citations · 957 across the 13 of their papers we have counts for
14 papers
einspace: Searching for Neural Architectures from Fundamental Operations
Linus Ericsson, Miguel Espinosa, Chenhongyi Yang +5
Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional str…
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
Kiyoon Kim, Shreyank N Gowda, Panagiotis Eustratiadis +2
Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shi…
Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months
Fady Rezk, Antreas Antoniou, Henry Gouk +1
We analyze VeLO (versatile learned optimizer), the largest scale attempt to train a general purpose "foundational" optimizer to date. VeLO was trained on thousands of machine learn…
Development of a Deep Learning Method to Identify Acute Ischemic Stroke Lesions on Brain CT
Alessandro Fontanella, Wenwen Li, Grant Mair +6
Computed Tomography (CT) is commonly used to image acute ischemic stroke (AIS) patients, but its interpretation by radiologists is time-consuming and subject to inter-observer vari…
Challenges of building medical image datasets for development of deep learning software in stroke
Alessandro Fontanella, Wenwen Li, Grant Mair +7
Despite the large amount of brain CT data generated in clinical practice, the availability of CT datasets for deep learning (DL) research is currently limited. Furthermore, the dat…
ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging
Alessandro Fontanella, Antreas Antoniou, Wenwen Li +4
In some medical imaging tasks and other settings where only small parts of the image are informative for the classification task, traditional CNNs can sometimes struggle to general…
Contrastive Meta-Learning for Partially Observable Few-Shot Learning
Adam Jelley, Amos Storkey, Antreas Antoniou +1
Many contrastive and meta-learning approaches learn representations by identifying common features in multiple views. However, the formalism for these approaches generally assumes…
Defining Benchmarks for Continual Few-Shot Learning
Antreas Antoniou, Massimiliano Patacchiola, Mateusz Ochal +1
Both few-shot and continual learning have seen substantial progress in the last years due to the introduction of proper benchmarks. That being said, the field has still to frame a…
Meta-Learning in Neural Networks: A Survey
Timothy Hospedales, Antreas Antoniou, Paul Micaelli +1
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratc…
Learning to learn via Self-Critique
Antreas Antoniou, Amos Storkey
In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same ta…
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
Antreas Antoniou, Amos Storkey
The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning…
Dilated DenseNets for Relational Reasoning
Antreas Antoniou, Agnieszka Słowik, Elliot J. Crowley +1
Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning. This has recently been remedied with the introduction of a plug-in…
How to train your MAML
Antreas Antoniou, Harrison Edwards, Amos Storkey
The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic…
Data Augmentation Generative Adversarial Networks
Antreas Antoniou, Amos Storkey, Harrison Edwards
Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviate…