4 papers
Preserving Angles Improves Feature Distillation
Evelyn J. Mannix, Liam Hodgkinson, Howard Bondell
Knowledge distillation methods compress models by training a student network using the classification outputs of a high quality teacher model, but can fail to effectively transfer…
ComFe: An Interpretable Head for Vision Transformers
Evelyn J. Mannix, Liam Hodgkinson, Howard Bondell
Interpretable computer vision models explain their classifications through comparing the distances between the local embeddings of an image and a set of prototypes that represent t…
A Mixture of Exemplars Approach for Efficient Out-of-Distribution Detection with Foundation Models
Evelyn Mannix, Howard Bondell
One of the early weaknesses identified in deep neural networks trained for image classification tasks was their inability to provide low confidence predictions on out-of-distributi…
An interpretable approach to automating the assessment of biofouling in video footage
Evelyn J. Mannix, Bartholomew A. Woodham
Biofouling$\unicode{x2013}$communities of organisms that grow on hard surfaces immersed in water$\unicode{x2013}$provides a pathway for the spread of invasive marine species and di…