Denoising diffusion models have emerged as the go-to framework for solvi...
Score-based generative models have demonstrated highly promising results...
Classical physical modelling with associated numerical simulation
(model...
Learned inverse problem solvers exhibit remarkable performance in
applic...
The deep image prior (DIP) is a well-established unsupervised deep learn...
Critical applications, such as in the medical field, require the rapid
p...
Recent years have witnessed a growth in mathematics for deep learning–wh...
We present a sample-efficient deep learning strategy for topology
optimi...
Learning neural networks using only a small amount of data is an importa...
In this work, we focus on connections between K-means clustering approac...
Magnetic particle imaging (MPI) is an imaging modality exploiting the
no...
We present a learned unsupervised denoising method for arbitrary types o...
One important property of imaging modalities and related applications is...
Filtered back projection (FBP) methods are the most widely used
reconstr...
Neural networks have recently been established as a viable classificatio...
Deep Learning approaches for solving Inverse Problems in imaging have be...
Recently the field of inverse problems has seen a growing usage of
mathe...
Recent studies on the adversarial vulnerability of neural networks have ...
The present paper studies the so called deep image prior (DIP) technique...
Despite their prevalence in neural networks we still lack a thorough
the...
Motivated by applications in hyperspectral imaging we investigate method...
Studying the invertibility of deep neural networks (DNNs) provides a
pri...
Motivation: Tumor classification using Imaging Mass Spectrometry (IMS) d...