Janis Keuper

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.

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.

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.

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.

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.