• Analysis of Deep Convolutional Neural Networks Using Tensor Kernels and Matrix-Based Entropy 

      Wickstrøm, Kristoffer; Løkse, Sigurd Eivindson; Kampffmeyer, Michael; Yu, Shujian; Príncipe, José C.; Jenssen, Robert (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-06-03)
      The aquaculture industry is expanding to meet the daily requirements of humanity from high-quality seafood. In this regard, intensive aquaculture systems are suggested, resulting in high production but being challenged with immunosuppression and disease invaders. Antibiotics were used for a long time to protect and treat aquatic animals; however, continuous use led to severe food safety issues, ...
    • Analysis of Deep Convolutional Neural Networks Using Tensor Kernels and Matrix-Based Entropy 

      Wickstrøm, Kristoffer Knutsen; Løkse, Sigurd Eivindson; Kampffmeyer, Michael Christian; Yu, Shujian; Príncipe, José C.; Jenssen, Robert (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-06-03)
      Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently to gain insight into, among others, DNNs’ generalization ability. However, it is by no means obvious how to estimate the mutual information (MI) between each hidden layer and the input/desired output to construct the IP. For instance, hidden layers with many neurons require MI estimators ...
    • 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; Tidsskriftartikkel; Peer reviewed, 2023-08-22)
      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 a few points (hubs) occur frequently in multiple nearest neighbour lists of other points. Hubness negatively impacts distance-based classification when hubs from one class appear ...
    • The Kernelized Taylor Diagram 

      Wickstrøm, Kristoffer; Johnson, Juan Emmanuel; Løkse, Sigurd Eivindson; Camps-Valls, Gusatu; Mikalsen, Karl Øyvind; Kampffmeyer, Michael; Jenssen, Robert (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-02)
      This paper presents the kernelized Taylor diagram, a graphical framework for visualizing similarities between data populations. The kernelized Taylor diagram builds on the widely used Taylor diagram, which is used to visualize similarities between populations. However, the Taylor diagram has several limitations such as not capturing non-linear relationships and sensitivity to outliers. To address ...
    • 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; Tidsskriftartikkel; Peer reviewed, 2023-08-22)
      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 slowing the progress of the field. To address this, we present Deep-MVC, a unified framework for deep MVC that includes many recent methods as instances. We leverage our framework to ...
    • Reconsidering Representation Alignment for Multi-View Clustering 

      Trosten, Daniel Johansen; Løkse, Sigurd Eivindson; Jenssen, Robert; Kampffmeyer, Michael (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-11-13)
      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 naïvely aligning representation distributions. We demonstrate that these drawbacks both lead to less separable clusters in the representation space, and inhibit the model’s ability to prioritize views. Based on these ...
    • RELAX: Representation Learning Explainability 

      Wickstrøm, Kristoffer; Trosten, Daniel Johansen; Løkse, Sigurd Eivindson; Boubekki, Ahcene; Mikalsen, Karl Øyvind; Kampffmeyer, Michael; Jenssen, Robert (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-03-11)
      Despite the significant improvements that self-supervised representation learning has led to when learning from unlabeled data, no methods have been developed that explain what influences the learned representation. We address this need through our proposed approach, RELAX, which is the first approach for attribution-based explanations of representations. Our approach can also model the uncertainty ...