54 citations · 61 across the 10 of their papers we have counts for
10 papers
PU-UNet: Stable Multiplicative Interactions for Medical Image Segmentation
Ziyuan Li, Osamah Sufyan, Uwe Jaekel +1
Many dense prediction networks rely on additive feature transformations and model higher-order feature interactions only implicitly. Product units provide an explicit mechanism for…
Product units in gated recurrent units improve nuclear-mass prediction
Ziyuan Li, Paulo S. A. Freitas, John W. Clark +1
The prediction of masses of atomic nuclei using machine learning can complement theoretical models and advance the exploration of poorly known domains of the nuclear chart. We prop…
Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks
Ziyuan Li, Uwe Jaekel, Babette Dellen
Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, lead…
Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation
Osamah Sufyan, Martin Brückmann, Ralph Wickenhöfer +2
In CT angiography, the accurate segmentation of abdominal aortic aneurysms (AAAs) is difficult due to large anatomical variability, low-contrast vessel boundaries, and the close pr…
PURe: A Plug-and-Play Product-Unit Residual Module for Vision Networks
Ziyuan Li, Uwe Jaekel, Babette Dellen
Modern vision networks are dominated by additive local transformations, whereas explicit multiplicative local interactions remain underexplored. Product units offer a direct approa…
Classification of data with a qudit, a geometric approach
A. Mandilara, B. Dellen, U. Jaekel +2
We propose a model for data classification using isolated quantum -level systems or else qudits. The procedure consists of an encoding phase where classical data are mapped on t…
Predicting nuclear masses with product-unit networks
Babette Dellen, Uwe Jaekel, Paulo S. A. Freitas +1
Accurate estimation of nuclear masses and their prediction beyond the experimentally explored domains of the nuclear landscape are crucial to an understanding of the fundamental or…
3D object reconstruction and 6D-pose estimation from 2D shape for robotic grasping of objects
Marcell Wolnitza, Osman Kaya, Tomas Kulvicius +2
We propose a method for 3D object reconstruction and 6D-pose estimation from 2D images that uses knowledge about object shape as the primary key. In the proposed pipeline, recognit…
Feature selection of neural networks is skewed towards the less abstract cue
Marcell Wolnitza, Babette Dellen
Artificial neural networks (ANNs) have become an important tool for image classification with many applications in research and industry. However, it remains largely unknown how re…
Synchronization from Disordered Driving Forces in Arrays of Coupled Oscillators
Sebastian F. Brandt, Babette K. Dellen, Ralf Wessel
The effects of disorder in external forces on the dynamical behavior of coupled nonlinear oscillator networks are studied. When driven synchronously, i.e., all driving forces have…