4 citations · 8 across the 4 of their papers we have counts for
5 papers
On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering
Daniel J. Trosten, Sigurd Løkse, Robert Jenssen +1
Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of self-supervision-b…
Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
Daniel J. Trosten, Rwiddhi Chakraborty, Sigurd Løkse +3
Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are pron…
RELAX: Representation Learning Explainability
Kristoffer K. Wickstrøm, Daniel J. Trosten, Sigurd Løkse +4
Despite the significant improvements that representation learning via self-supervision has led to when learning from unlabeled data, no methods exist that explain what influences t…
Reconsidering Representation Alignment for Multi-view Clustering
Daniel J. Trosten, Sigurd Løkse, Robert Jenssen +1
Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering. However, we identify several drawbacks with na…
Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series
Daniel J. Trosten, Andreas S. Strauman, Michael Kampffmeyer +1
The task of clustering unlabeled time series and sequences entails a particular set of challenges, namely to adequately model temporal relations and variable sequence lengths. If t…