J
Janis Keuper
Researcher at Fraunhofer Society
Publications - 73
Citations - 881
Janis Keuper is an academic researcher from Fraunhofer Society. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 10, co-authored 49 publications receiving 493 citations. Previous affiliations of Janis Keuper include Kaiserslautern University of Technology & Fraunhofer Institute for Industrial Mathematics.
Papers
More filters
Proceedings ArticleDOI
Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions
TL;DR: This paper proposes to add a novel spectral regularization term to the training optimization objective and shows that this approach not only allows to train spectral consistent GANs that are avoiding high frequency errors but also shows that a correct approximation of the frequency spectrum has positive effects on the training stability and output quality of generative networks.
Posted Content
Unmasking DeepFakes with simple Features
TL;DR: This work presents a simple way to detect fake face images - so-called DeepFakes, based on a classical frequency domain analysis followed by basic classifier, which shows very good results using only a few annotated training samples and even achieved good accuracies in fully unsupervised scenarios.
Proceedings ArticleDOI
Distributed training of deep neural networks: theoretical and practical limits of parallel scalability
Janis Keuper,Franz-Josef Preundt +1 more
TL;DR: In this article, the authors present a theoretical analysis and practical evaluation of the main bottlenecks towards a scalable distributed solution for the training of deep neural networks (DNNs), and show that the current state of the art approach, using data-parallelized Stochastic gradient descent (SGD), is quickly turning into a vastly communication bound problem.
Posted Content
Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability
TL;DR: The presented results show, that the current state of the art approach, using data-parallelized Stochastic Gradient Descent (SGD), is quickly turning into a vastly communication bound problem, leading to poor scalability of DNN training in most practical scenarios.
Journal ArticleDOI
Extracting horizon surfaces from 3D seismic data using deep learning
TL;DR: This work has formulated horizon picking as a multiclass segmentation problem and solved it by supervised training of a 3D convolutional neural network by designing an efficient architecture to analyze the data over multiple scales while keeping memory and computational needs to a practical level.