Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Knigge, David M"'
Autor:
Knigge, David M., Wessels, David R., Valperga, Riccardo, Papa, Samuele, Sonke, Jan-Jakob, Gavves, Efstratios, Bekkers, Erik J.
Recently, Conditional Neural Fields (NeFs) have emerged as a powerful modelling paradigm for PDEs, by learning solutions as flows in the latent space of the Conditional NeF. Although benefiting from favourable properties of NeFs such as grid-agnostic
Externí odkaz:
http://arxiv.org/abs/2406.06660
Autor:
Wessels, David R, Knigge, David M, Papa, Samuele, Valperga, Riccardo, Vadgama, Sharvaree, Gavves, Efstratios, Bekkers, Erik J
Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone Neural Field (NeF) to reconstruct the sample. However, ex
Externí odkaz:
http://arxiv.org/abs/2406.05753
Autor:
Papa, Samuele, Knigge, David M., Valperga, Riccardo, Moriakov, Nikita, Kofinas, Miltos, Sonke, Jan-Jakob, Gavves, Efstratios
Conventional Computed Tomography (CT) methods require large numbers of noise-free projections for accurate density reconstructions, limiting their applicability to the more complex class of Cone Beam Geometry CT (CBCT) reconstruction. Recently, deep
Externí odkaz:
http://arxiv.org/abs/2307.08351
Autor:
Knigge, David M., Romero, David W., Gu, Albert, Gavves, Efstratios, Bekkers, Erik J., Tomczak, Jakub M., Hoogendoorn, Mark, Sonke, Jan-Jakob
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN architectures.
Externí odkaz:
http://arxiv.org/abs/2301.10540
Autor:
Romero, David W., Knigge, David M., Gu, Albert, Bekkers, Erik J., Gavves, Efstratios, Tomczak, Jakub M., Hoogendoorn, Mark
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework. However, performant CNN architectures must be tailored
Externí odkaz:
http://arxiv.org/abs/2206.03398
Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular G-CNNs, an
Externí odkaz:
http://arxiv.org/abs/2110.13059