Search Results for author:
Found 7 papers, 2 papers with code
Cluster Metric Sensitivity to Irrelevant Features
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.
Fast Data Driven Estimation of Cluster Number in Multiplex Images using Embedded Density Outliers
In this work we demonstrate our method using 45 multiplex imaging mass cytometry datasets.
A Generic Self-Supervised Framework of Learning Invariant Discriminative Features
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.
Enhanced Transfer Learning Through Medical Imaging and Patient Demographic Data Fusion
In this work we examine the performance enhancement in classification of medical imaging data when image features are combined with associated non-image data.
Combining Image Features and Patient Metadata to Enhance Transfer Learning
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.
Information Maximization Clustering via Multi-View Self-Labelling
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
Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets.
