4k citations
- Nvidia (United States)US24 papers
- University of TorontoCA11 papers
- Stanford UniversityUS8 papers
- University of California, MercedUS6 papers
- University of WashingtonUS6 papers
- Massachusetts Institute of TechnologyUS5 papers
- Duke UniversityUS4 papers
- Google (United States)US4 papers
- Imperial College LondonGB4 papers
- Nanyang Technological UniversitySG4 papers
- National Taiwan UniversityTW4 papers
- Technical University of MunichDE4 papers
38 papers · 1 filter
LBcuda: a high-performance CUDA port of LBsoft for simulation of colloidal systems
Fabio Bonaccorso, Marco Lauricella, Andrea Montessori +5
We present LBcuda, a GPU accelerated version of LBsoft, our open-source MPI-based software for the simulation of multi-component colloidal flows. We describe the design principles,…
EditGAN: High-Precision Semantic Image Editing
Huan Ling, Karsten Kreis, Daiqing Li +3
Generative adversarial networks (GANs) have recently found applications in image editing. However, most GAN based image editing methods often require large scale datasets with sema…
Spatio-Temporal Variational Gaussian Processes
Oliver Hamelijnck, William J. Wilkinson, Niki A. Loppi +2
We introduce a scalable approach to Gaussian process inference that combines spatio-temporal filtering with natural gradient variational inference, resulting in a non-conjugate GP…
Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging
Andriy Myronenko, Ziyue Xu, Dong Yang +2
Multiple instance learning (MIL) is a key algorithm for classification of whole slide images (WSI). Histology WSIs can have billions of pixels, which create enormous computational…
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer
Wenzheng Chen, Joey Litalien, Jun Gao +5
We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiable renderers. Many previous learning-based approaches fo…
A Data-Centric Approach for Training Deep Neural Networks with Less Data
Mohammad Motamedi, Nikolay Sakharnykh, Tim Kaldewey
While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data. Ho…