T
Timothy M. Hospedales
Researcher at University of Edinburgh
Publications - 326
Citations - 23023
Timothy M. Hospedales is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Computer science & Sketch. The author has an hindex of 59, co-authored 288 publications receiving 14711 citations. Previous affiliations of Timothy M. Hospedales include Imperial College London & Samsung.
Papers
More filters
Proceedings ArticleDOI
Learning to Compare: Relation Network for Few-Shot Learning
TL;DR: A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
Posted Content
Learning to Compare: Relation Network for Few-Shot Learning
TL;DR: Relation Network (RN) as mentioned in this paper learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting.
Proceedings ArticleDOI
Deep Mutual Learning
TL;DR: In this paper, a deep mutual learning (DML) strategy is proposed to transfer knowledge from a teacher to a student network, where an ensemble of students learn collaboratively and teach each other throughout the training process.
Posted Content
Meta-Learning in Neural Networks: A Survey
TL;DR: A new taxonomy is proposed that provides a more comprehensive breakdown of the space of meta-learning methods today, including few-shot learning, reinforcement learning and architecture search, and promising applications and successes.
Proceedings ArticleDOI
Deeper, Broader and Artier Domain Generalization
TL;DR: In this article, a low-rank parameterized CNN model is proposed for domain generalization, which can learn from multiple training domains and extract a domain-agnostic model that can then be applied to an unseen domain.