no code implementations • 19 Feb 2024 • Miles McCrory, Spencer A. Thomas
We observe a resilience to very high proportions of irrelevant features for adjusted rand index (ARI) and normalised mutual information (NMI) when the irrelevant features are Gaussian distributed.
no code implementations • 21 Jul 2022 • Spencer A. Thomas
In this work we demonstrate our method using 45 multiplex imaging mass cytometry datasets.
no code implementations • 14 Feb 2022 • Foivos Ntelemis, Yaochu Jin, Spencer A. Thomas
Specifically, the prior transformation functions are replaced with a self-transformation mechanism, derived through an unsupervised training process of adversarial training, for imposing invariant representations.
no code implementations • 29 Nov 2021 • Spencer A. Thomas
In this work we examine the performance enhancement in classification of medical imaging data when image features are combined with associated non-image data.
no code implementations • 8 Oct 2021 • Spencer A. Thomas
In this work, we compare the performance of six state-of-the-art deep neural networks in classification tasks when using only image features, to when these are combined with patient metadata.
1 code implementation • 12 Mar 2021 • Foivos Ntelemis, Yaochu Jin, Spencer A. Thomas
Specifically, the proposed clustering objective employs mutual information, and maximizes the dependency between the integrated discrete representation and a discrete probability distribution.
Ranked #2 on Image Clustering on Tiny-ImageNet
1 code implementation • 8 Nov 2020 • Foivos Ntelemis, Yaochu Jin, Spencer A. Thomas
Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets.