Search Results for author: Elena Marchiori

Found 18 papers, 1 papers with code

Multi-view analysis of unregistered medical images using cross-view transformers

no code implementations21 Mar 2021 Gijs van Tulder, Yao Tong, Elena Marchiori

We present a novel cross-view transformer method to transfer information between unregistered views at the level of spatial feature maps.

Gaussian Processes with Skewed Laplace Spectral Mixture Kernels for Long-term Forecasting

no code implementations8 Nov 2020 Kai Chen, Twan van Laarhoven, Elena Marchiori

The heavy tail and skewness characteristics of such distributions in the spectral domain allow to capture long-range covariance of the signal in the time domain.

Gaussian Processes Time Series

Unsupervised Domain Adaptation using Graph Transduction Games

no code implementations6 May 2019 Sebastiano Vascon, Sinem Aslan, Alessandro Torcinovich, Twan van Laarhoven, Elena Marchiori, Marcello Pelillo

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain.

Object Recognition Unsupervised Domain Adaptation

Vendor-independent soft tissue lesion detection using weakly supervised and unsupervised adversarial domain adaptation

no code implementations14 Aug 2018 Joris van Vugt, Elena Marchiori, Ritse Mann, Albert Gubern-Mérida, Nikita Moriakov, Jonas Teuwen

We analyze two transfer learning settings: 1) unsupervised transfer, where Hologic data with soft lesion annotation at pixel level and Siemens unlabelled data are used to annotate images in the latter data; 2) weak supervised transfer, where exam level labels for images from the Siemens mammograph are available.

Domain Adaptation Transfer Learning

Multi-Output Convolution Spectral Mixture for Gaussian Processes

no code implementations7 Aug 2018 Kai Chen, Perry Groot, Jinsong Chen, Elena Marchiori

Multi-output Gaussian processes (MOGPs) are recently extended by using spectral mixture kernel, which enables expressively pattern extrapolation with a strong interpretation.

Gaussian Processes

Generalized Spectral Mixture Kernels for Multi-Task Gaussian Processes

no code implementations3 Aug 2018 Kai Chen, Perry Groot, Jinsong Chen, Elena Marchiori

Multi-Task Gaussian processes (MTGPs) have shown a significant progress both in expressiveness and interpretation of the relatedness between different tasks: from linear combinations of independent single-output Gaussian processes (GPs), through the direct modeling of the cross-covariances such as spectral mixture kernels with phase shift, to the design of multivariate covariance functions based on spectral mixture kernels which model delays among tasks in addition to phase differences, and which provide a parametric interpretation of the relatedness across tasks.

Gaussian Processes

Novel Compressible Adaptive Spectral Mixture Kernels for Gaussian Processes with Sparse Time and Phase Delay Structures

no code implementations1 Aug 2018 Kai Chen, Yijue Dai, Feng Yin, Elena Marchiori, Sergios Theodoridis

By verifying the presence of dependencies between function components using Gaussian conditionals and posterior covariance, we first propose a new SM kernel variant with a time and phase delay dependency structure (SMD) and then provide a structure adaptation (SA) algorithm for the SMD.

Gaussian Processes Model Compression

Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

no code implementations12 Apr 2018 Jeroen Manders, Twan van Laarhoven, Elena Marchiori

Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level.

Image Classification Unsupervised Domain Adaptation

Domain Adaptation with Randomized Expectation Maximization

1 code implementation20 Mar 2018 Twan van Laarhoven, Elena Marchiori

Despite their success, state of the art methods based on this approach are either involved or unable to directly scale to data with many features.

Domain Adaptation Transfer Learning

Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders

no code implementations14 Sep 2017 Nastaran Mohammadian Rad, Seyed Mostafa Kia, Calogero Zarbo, Twan van Laarhoven, Giuseppe Jurman, Paola Venuti, Elena Marchiori, Cesare Furlanello

Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors.

Ensemble Learning Transfer Learning

Unsupervised Domain Adaptation with Random Walks on Target Labelings

no code implementations16 Jun 2017 Twan van Laarhoven, Elena Marchiori

Unsupervised Domain Adaptation (DA) is used to automatize the task of labeling data: an unlabeled dataset (target) is annotated using a labeled dataset (source) from a related domain.

Unsupervised Domain Adaptation

Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation

no code implementations25 Feb 2017 Mohsen Ghafoorian, Alireza Mehrtash, Tina Kapur, Nico Karssemeijer, Elena Marchiori, Mehran Pesteie, Charles R. G. Guttmann, Frank-Erik de Leeuw, Clare M. Tempany, Bram van Ginneken, Andriy Fedorov, Purang Abolmaesumi, Bram Platel, William M. Wells III

In this study, we aim to answer the following central questions regarding domain adaptation in medical image analysis: Given a fitted legacy model, 1) How much data from the new domain is required for a decent adaptation of the original network?

Domain Adaptation Lesion Segmentation +1

Local Network Community Detection with Continuous Optimization of Conductance and Weighted Kernel K-Means

no code implementations21 Jan 2016 Twan van Laarhoven, Elena Marchiori

We investigate the relation of conductance with weighted kernel k-means for a single community, which leads to the introduction of a new objective function, $\sigma$-conductance.

Local Community Detection

Resolution-limit-free and local Non-negative Matrix Factorization quality functions for graph clustering

no code implementations22 Jul 2014 Twan van Laarhoven, Elena Marchiori

We argue that this is a desirable property, provide conditions under which NMF quality functions are local, and propose a novel class of local probabilistic NMF quality functions for soft graph clustering.

Graph Clustering graph partitioning

Axioms for graph clustering quality functions

no code implementations15 Aug 2013 Twan van Laarhoven, Elena Marchiori

This motivates the derivation of a new family of quality functions, adaptive scale modularity, which does satisfy the proposed axioms.

Community Detection Graph Clustering

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