no code implementations • 27 Feb 2024 • David Torpey, Lawrence Pratt, Richard Klein
Additionally, we provide a large-scale unlabelled EL image dataset of $22000$ images, and a $642$-image labelled semantic segmentation EL dataset, for further research in developing self- and semi-supervised training techniques in this domain.
no code implementations • 23 Feb 2024 • David Torpey, Richard Klein
Often, applications of self-supervised learning to 3D medical data opt to use 3D variants of successful 2D network architectures.
no code implementations • 14 Feb 2024 • David Torpey, Richard Klein
The standard approach to modern self-supervised learning is to generate random views through data augmentations and minimise a loss computed from the representations of these views.
no code implementations • 27 Jul 2022 • David Torpey, Richard Klein
It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training.
no code implementations • 12 Jan 2021 • David Torpey, Richard Klein
We show how the inclusion of this module to regress the parameters of an affine transformation or homography, in addition to the original contrastive objective, improves both performance and learning speed.
no code implementations • 19 Feb 2020 • David Torpey, Turgay Celik
This paper proposes a simple yet effective method for human action recognition in video.
no code implementations • 19 Feb 2020 • Ziyad Jappie, David Torpey, Turgay Celik
Video summarisation can be posed as the task of extracting important parts of a video in order to create an informative summary of what occurred in the video.