Blar i Publikasjoner fra Cristin på forfatter "Trosten, Daniel Johansen"
-
Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
Trosten, Daniel Johansen; Chakraborty, Rwiddhi; Løkse, Sigurd Eivindson; Wickstrøm, Kristoffer; Jenssen, Robert; Kampffmeyer, Michael (Journal article; Peer reviewed, 2023)Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, where ... -
On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering
Trosten, Daniel Johansen; Løkse, Sigurd Eivindson; Jenssen, Robert; Kampffmeyer, Michael (Journal article; Peer reviewed, 2023)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-based methods for deep MVC, potentially ... -
Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective
Trosten, Daniel Johansen; Jenssen, Robert; Kampffmeyer, Michael (Journal article; Peer reviewed, 2021)