Search Results for author: Robert Jenssen

Found 62 papers, 29 papers with code

View it like a radiologist: Shifted windows for deep learning augmentation of CT images

1 code implementation25 Nov 2023 Eirik A. Østmo, Kristoffer K. Wickstrøm, Keyur Radiya, Michael C. Kampffmeyer, Robert Jenssen

Our method outperforms classical intensity augmentations as well as the intensity augmentation pipeline of the popular nn-UNet on multiple datasets.

Computed Tomography (CT) Lesion Segmentation

The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making

no code implementations21 Jan 2023 Shujian Yu, Hongming Li, Sigurd Løkse, Robert Jenssen, José C. Príncipe

In this paper, we extend the classic CS divergence to quantify the closeness between two conditional distributions and show that the developed conditional CS divergence can be simply estimated by a kernel density estimator from given samples.

Decision Making Time Series +1

A clinically motivated self-supervised approach for content-based image retrieval of CT liver images

2 code implementations11 Jul 2022 Kristoffer Knutsen Wickstrøm, Eirik Agnalt Østmo, Keyur Radiya, Karl Øyvind Mikalsen, Michael Christian Kampffmeyer, Robert Jenssen

We address these limitations by (1) proposing a self-supervised learning framework that incorporates domain-knowledge into the training procedure and (2) providing the first representation learning explainability analysis in the context of CBIR of CT liver images.

Content-Based Image Retrieval Representation Learning +2

Principle of Relevant Information for Graph Sparsification

1 code implementation31 May 2022 Shujian Yu, Francesco Alesiani, Wenzhe Yin, Robert Jenssen, Jose C. Principe

Graph sparsification aims to reduce the number of edges of a graph while maintaining its structural properties.

Multi-Task Learning

The Kernelized Taylor Diagram

1 code implementation18 May 2022 Kristoffer Wickstrøm, J. Emmanuel Johnson, Sigurd Løkse, Gustau Camps-Valls, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen

Our proposed kernelized Taylor diagram is capable of visualizing similarities between populations with minimal assumptions of the data distributions.

Data Visualization

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

no code implementations7 May 2022 Kaizhong Zheng, Shujian Yu, Baojuan Li, Robert Jenssen, Badong Chen

Developing a new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus.

Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels

1 code implementation3 Mar 2022 Stine Hansen, Srishti Gautam, Robert Jenssen, Michael Kampffmeyer

Motivated by this, and the observation that the foreground class (e. g., one organ) is relatively homogeneous, we propose a novel anomaly detection-inspired approach to few-shot medical image segmentation in which we refrain from modeling the background explicitly.

Anomaly Detection Cardiac Segmentation +5

Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagation

no code implementations10 Jan 2022 Srishti Gautam, Marina M. -C. Höhne, Stine Hansen, Robert Jenssen, Michael Kampffmeyer

The recent trend of integrating multi-source Chest X-Ray datasets to improve automated diagnostics raises concerns that models learn to exploit source-specific correlations to improve performance by recognizing the source domain of an image rather than the medical pathology.

Pneumonia Detection

RELAX: Representation Learning Explainability

1 code implementation19 Dec 2021 Kristoffer K. Wickstrøm, Daniel J. Trosten, Sigurd Løkse, Ahcène Boubekki, Karl Øyvind Mikalsen, Michael C. Kampffmeyer, Robert Jenssen

Our approach can also model the uncertainty in its explanations, which is essential to produce trustworthy explanations.

Representation Learning

Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks

1 code implementation6 Nov 2021 Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

To this end, we propose a new multi-modality network (MultiModNet) for land cover mapping of multi-modal remote sensing data based on a novel pyramid attention fusion (PAF) module and a gated fusion unit (GFU).

Land Cover Classification

Discriminative Multimodal Learning via Conditional Priors in Generative Models

1 code implementation9 Oct 2021 Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen

Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data.

Reconsidering Representation Alignment for Multi-view Clustering

1 code implementation CVPR 2021 Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer

Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering.

Clustering Contrastive Learning

Joint Optimization of an Autoencoder for Clustering and Embedding

1 code implementation7 Dec 2020 Ahcène Boubekki, Michael Kampffmeyer, Robert Jenssen, Ulf Brefeld

That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding.

Clustering Deep Clustering

Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series

1 code implementation16 Oct 2020 Kristoffer Wickstrøm, Karl Øyvind Mikalsen, Michael Kampffmeyer, Arthur Revhaug, Robert Jenssen

A measure of uncertainty in the relevance scores is computed by taking the standard deviation across the relevance scores produced by each model in the ensemble, which in turn is used to make the explanations more reliable.

Time Series Time Series Analysis

SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation

no code implementations3 Sep 2020 Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance.

Graph Reconstruction Open-Ended Question Answering +2

Code-Aligned Autoencoders for Unsupervised Change Detection in Multimodal Remote Sensing Images

1 code implementation15 Apr 2020 Luigi T. Luppino, Mads A. Hansen, Michael Kampffmeyer, Filippo M. Bianchi, Gabriele Moser, Robert Jenssen, Stian N. Anfinsen

We propose to extract relational pixel information captured by domain-specific affinity matrices at the input and use this to enforce alignment of the code spaces and reduce the impact of change pixels on the learning objective.

Change Detection Translation

Self-Constructing Graph Convolutional Networks for Semantic Labeling

1 code implementation15 Mar 2020 Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs.

Graph Reconstruction Knowledge Graphs

A Kernel to Exploit Informative Missingness in Multivariate Time Series from EHRs

no code implementations27 Feb 2020 Karl Øyvind Mikalsen, Cristina Soguero-Ruiz, Robert Jenssen

A large fraction of the electronic health records (EHRs) consists of clinical measurements collected over time, such as lab tests and vital signs, which provide important information about a patient's health status.

Ensemble Learning Imputation +2

Leveraging tensor kernels to reduce objective function mismatch in deep clustering

2 code implementations20 Jan 2020 Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer

In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the reconstruction and clustering objectives.

Clustering Deep Clustering +1

LS-Net: Fast Single-Shot Line-Segment Detector

no code implementations19 Dec 2019 Van Nhan Nguyen, Robert Jenssen, Davide Roverso

In recent years, many vision-based techniques have been proposed to detect power lines to facilitate self-driving UAVs and automatic obstacle avoidance.

Data Augmentation Edge Detection +1

Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels

no code implementations25 Sep 2019 Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, Robert Jenssen

In this paper, we propose an IP analysis using the new matrix--based R\'enyi's entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data.

Information Plane

Information Plane Analysis of Deep Neural Networks via Matrix--Based Renyi's Entropy and Tensor Kernels

no code implementations25 Sep 2019 Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, Robert Jenssen

In this paper, we propose an IP analysis using the new matrix--based R\'enyi's entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data.

Information Plane

Road Mapping In LiDAR Images Using A Joint-Task Dense Dilated Convolutions Merging Network

no code implementations7 Sep 2019 Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

This pushes the network towards learning more robust representations that are expected to boost the ultimate performance of the main task.

Computational Efficiency Multi-class Classification

Dense Dilated Convolutions Merging Network for Semantic Mapping of Remote Sensing Images

1 code implementation30 Aug 2019 Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

We propose a network for semantic mapping called the Dense Dilated Convolutions Merging Network (DDCM-Net) to provide a deep learning approach that can recognize multi-scale and complex shaped objects with similar color and textures, such as buildings, surfaces/roads, and trees in very high resolution remote sensing images.

Time series cluster kernels to exploit informative missingness and incomplete label information

no code implementations10 Jul 2019 Karl Øyvind Mikalsen, Cristina Soguero-Ruiz, Filippo Maria Bianchi, Arthur Revhaug, Robert Jenssen

To overcome this limitation, we present a kernel capable of exploiting the potentially rich information in the missing values and patterns, as well as the information from the observed data.

Ensemble Learning Imputation +2

Deep Generative Models for Reject Inference in Credit Scoring

1 code implementation12 Apr 2019 Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen

Reject inference is the process of attempting to infer the creditworthiness status of the rejected applications.

Learning Latent Representations of Bank Customers With The Variational Autoencoder

no code implementations14 Mar 2019 Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen

We show that it is possible to steer the latent representations in the latent space of the VAE using the Weight of Evidence and forming a specific grouping of the data that reflects the customers' creditworthiness.

Clustering Management +1

Noisy multi-label semi-supervised dimensionality reduction

no code implementations20 Feb 2019 Karl Øyvind Mikalsen, Cristina Soguero-Ruiz, Filippo Maria Bianchi, Robert Jenssen

With the proposed Noisy multi-label semi-supervised dimensionality reduction (NMLSDR) method, the noisy multi-labels are denoised and unlabeled data are labeled simultaneously via a specially designed label propagation algorithm.

Supervised dimensionality reduction

Deep Divergence-Based Approach to Clustering

no code implementations13 Feb 2019 Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Lorenzo Livi, Arnt-Børre Salberg, Robert Jenssen

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function.

Clustering Deep Clustering +1

Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series

no code implementations29 Nov 2018 Daniel J. Trosten, Andreas S. Strauman, Michael Kampffmeyer, Robert Jenssen

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.

Clustering Time Series +1

Multivariate Extension of Matrix-based Renyi's α-order Entropy Functional

1 code implementation23 Aug 2018 Shujian Yu, Luis Gonzalo Sanchez Giraldo, Robert Jenssen, Jose C. Principe

The matrix-based Renyi's \alpha-order entropy functional was recently introduced using the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS).

feature selection

The Deep Kernelized Autoencoder

no code implementations19 Jul 2018 Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Robert Jenssen, Lorenzo Livi

Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network.

Denoising

Segment-Based Credit Scoring Using Latent Clusters in the Variational Autoencoder

no code implementations7 Jun 2018 Rogelio Andrade Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen

We use the VAE and show that transforming the input data into a meaningful representation, it is possible to steer configurations in the latent space of the VAE.

Clustering Marketing

Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration

no code implementations18 Apr 2018 Shujian Yu, Kristoffer Wickstrøm, Robert Jenssen, Jose C. Principe

The matrix-based Renyi's \alpha-entropy functional and its multivariate extension were recently developed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS).

An Unsupervised Multivariate Time Series Kernel Approach for Identifying Patients with Surgical Site Infection from Blood Samples

no code implementations21 Mar 2018 Karl Øyvind Mikalsen, Cristina Soguero-Ruiz, Filippo Maria Bianchi, Arthur Revhaug, Robert Jenssen

A large fraction of the electronic health records consists of clinical measurements collected over time, such as blood tests, which provide important information about the health status of a patient.

General Classification Imputation +2

Learning compressed representations of blood samples time series with missing data

1 code implementation20 Oct 2017 Filippo Maria Bianchi, Karl Øyvind Mikalsen, Robert Jenssen

Clinical measurements collected over time are naturally represented as multivariate time series (MTS), which often contain missing data.

General Classification Time Series +1

Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks

no code implementations21 Sep 2017 Michael Kampffmeyer, Arnt-Børre Salberg, Robert Jenssen

Techniques to improve urban land cover classification performance in remote sensing include fusion of data from different sensors with different data modalities.

Decision Making General Classification +2

An overview and comparative analysis of Recurrent Neural Networks for Short Term Load Forecasting

no code implementations11 May 2017 Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen

Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet.

Load Forecasting Time Series +1

Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data

1 code implementation3 Apr 2017 Karl Øyvind Mikalsen, Filippo Maria Bianchi, Cristina Soguero-Ruiz, Robert Jenssen

An ensemble learning approach is exploited to ensure robustness to parameters by combining the clustering results of many GMM to form the final kernel.

Clustering Ensemble Learning +2

Spectral Clustering using PCKID - A Probabilistic Cluster Kernel for Incomplete Data

no code implementations23 Feb 2017 Sigurd Løkse, Filippo Maria Bianchi, Arnt-Børre Salberg, Robert Jenssen

In this paper, we propose PCKID, a novel, robust, kernel function for spectral clustering, specifically designed to handle incomplete data.

Clustering

A clustering approach to heterogeneous change detection

no code implementations10 Feb 2017 Luigi Tommaso Luppino, Stian Normann Anfinsen, Gabriele Moser, Robert Jenssen, Filippo Maria Bianchi, Sebastiano Serpico, Gregoire Mercier

Change detection in heterogeneous multitemporal satellite images is a challenging and still not much studied topic in remote sensing and earth observation.

Change Detection Clustering

Deep Kernelized Autoencoders

no code implementations8 Feb 2017 Michael Kampffmeyer, Sigurd Løkse, Filippo Maria Bianchi, Robert Jenssen, Lorenzo Livi

In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space.

Denoising

Temporal Overdrive Recurrent Neural Network

no code implementations18 Jan 2017 Filippo Maria Bianchi, Michael Kampffmeyer, Enrico Maiorino, Robert Jenssen

In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics.

Time Series Time Series Prediction

Multiplex visibility graphs to investigate recurrent neural networks dynamics

no code implementations10 Sep 2016 Filippo Maria Bianchi, Lorenzo Livi, Cesare Alippi, Robert Jenssen

We show that topological properties of such a multiplex reflect important features of RNN dynamics and are used to guide the tuning procedure.

Time Series Time Series Analysis

Manifold unwrapping using density ridges

no code implementations6 Apr 2016 Jonas Nordhaug Myhre, Matineh Shaker, Devrim Kaba, Robert Jenssen, Deniz Erdogmus

Research on manifold learning within a density ridge estimation framework has shown great potential in recent work for both estimation and de-noising of manifolds, building on the intuitive and well-defined notion of principal curves and surfaces.

Optimized Kernel Entropy Components

no code implementations9 Mar 2016 Emma Izquierdo-Verdiguier, Valero Laparra, Robert Jenssen, Luis Gómez-Chova, Gustau Camps-Valls

Results show that 1) OKECA returns projections with more expressive power than KECA, 2) the most successful rule for estimating the kernel parameter is based on maximum likelihood, and 3) OKECA is more robust to the selection of the length-scale parameter in kernel density estimation.

Density Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.