5 citations · 6 across the 7 of their papers we have counts for
7 papers
A Large-scale Evaluation of Pretraining Paradigms for the Detection of Defects in Electroluminescence Solar Cell Images
David Torpey, Lawrence Pratt, Richard Klein
Pretraining has been shown to improve performance in many domains, including semantic segmentation, especially in domains with limited labelled data. In this work, we perform a lar…
DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning
David Torpey, Richard Klein
Often, applications of self-supervised learning to 3D medical data opt to use 3D variants of successful 2D network architectures. Although promising approaches, they are significan…
Affine transformation estimation improves visual self-supervised learning
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…
On the robustness of self-supervised representations for multi-view object classification
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-…
Explicit homography estimation improves contrastive self-supervised learning
David Torpey, Richard Klein
The typical contrastive self-supervised algorithm uses a similarity measure in latent space as the supervision signal by contrasting positive and negative images directly or indire…
SummaryNet: A Multi-Stage Deep Learning Model for Automatic Video Summarisation
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. In this paper we intr…
Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines
David Torpey, Turgay Celik
This paper proposes a simple yet effective method for human action recognition in video. The proposed method separately extracts local appearance and motion features using state-of…