Search Results for author:
Found 3 papers, 2 papers with code
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.
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.
