176 citations · 262 across the 15 of their papers we have counts for
20 papers
Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
Patrick Grommelt, Louis Weiss, Franz-Josef Pfreundt +1
The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and mi…
Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
Kalun Ho, Franz-Josef Pfreundt, Janis Keuper +1
Over the last decade, the development of deep image classification networks has mostly been driven by the search for the best performance in terms of classification accuracy on sta…
SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain
Paula Harder, Franz-Josef Pfreundt, Margret Keuper +1
Despite the success of convolutional neural networks (CNNs) in many computer vision and image analysis tasks, they remain vulnerable against so-called adversarial attacks: Small, c…
Latent Space Conditioning on Generative Adversarial Networks
Ricard Durall, Kalun Ho, Franz-Josef Pfreundt +1
Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this tr…
Module Intersection for the Integration-by-Parts Reduction of Multi-Loop Feynman Integrals
Dominik Bendle, Janko Boehm, Wolfram Decker +4
In this manuscript, which is to appear in the proceedings of the conference "MathemAmplitude 2019" in Padova, Italy, we provide an overview of the module intersection method for th…
Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches
Kalun Ho, Janis Keuper, Franz-Josef Pfreundt +1
In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings.…
Local Facial Attribute Transfer through Inpainting
Ricard Durall, Franz-Josef Pfreundt, Janis Keuper
The term attribute transfer refers to the tasks of altering images in such a way, that the semantic interpretation of a given input image is shifted towards an intended direction,…
Scalable Hyperparameter Optimization with Lazy Gaussian Processes
Raju Ram, Sabine Müller, Franz-Josef Pfreundt +2
Most machine learning methods require careful selection of hyper-parameters in order to train a high performing model with good generalization abilities. Hence, several automatic s…
Unmasking DeepFakes with simple Features
Ricard Durall, Margret Keuper, Franz-Josef Pfreundt +1
Deep generative models have recently achieved impressive results for many real-world applications, successfully generating high-resolution and diverse samples from complex datasets…
Semi Few-Shot Attribute Translation
Ricard Durall, Franz-Josef Pfreundt, Janis Keuper
Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and…
GradVis: Visualization and Second Order Analysis of Optimization Surfaces during the Training of Deep Neural Networks
Avraam Chatzimichailidis, Franz-Josef Pfreundt, Nicolas R. Gauger +1
Current training methods for deep neural networks boil down to very high dimensional and non-convex optimization problems which are usually solved by a wide range of stochastic gra…
Object Segmentation using Pixel-wise Adversarial Loss
Ricard Durall, Franz-Josef Pfreundt, Ullrich Köthe +1
Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adver…
Integration-by-parts reductions of Feynman integrals using Singular and GPI-Space
Dominik Bendle, Janko Boehm, Wolfram Decker +5
We introduce an algebro-geometrically motived integration-by-parts (IBP) reduction method for multi-loop and multi-scale Feynman integrals, using a framework for massively parallel…
Stabilizing GANs with Soft Octave Convolutions
Ricard Durall, Franz-Josef Pfreundt, Janis Keuper
Motivated by recently published methods using frequency decompositions of convolutions (e.g. Octave Convolutions), we propose a novel convolution scheme to stabilize the training a…
Towards Massively Parallel Computations in Algebraic Geometry
Janko Boehm, Wolfram Decker, Anne Frühbis-Krüger +3
Introducing parallelism and exploring its use is still a fundamental challenge for the computer algebra community. In high performance numerical simulation, on the other hand, tran…
Sparsity in Deep Neural Networks - An Empirical Investigation with TensorQuant
Dominik Marek Loroch, Franz-Josef Pfreundt, Norbert Wehn +1
Deep learning is finding its way into the embedded world with applications such as autonomous driving, smart sensors and aug- mented reality. However, the computation of deep neura…
TensorQuant - A Simulation Toolbox for Deep Neural Network Quantization
Dominik Marek Loroch, Norbert Wehn, Franz-Josef Pfreundt +1
Recent research implies that training and inference of deep neural networks (DNN) can be computed with low precision numerical representations of the training/test data, weights an…
Using GPI-2 for Distributed Memory Paralleliziation of the Caffe Toolbox to Speed up Deep Neural Network Training
Martin Kuehn, Janis Keuper, Franz-Josef Pfreundt
Deep Neural Network (DNN) are currently of great inter- est in research and application. The training of these net- works is a compute intensive and time consuming task. To reduce…
Balancing the Communication Load of Asynchronously Parallelized Machine Learning Algorithms
Janis Keuper, Franz-Josef Pfreundt
Stochastic Gradient Descent (SGD) is the standard numerical method used to solve the core optimization problem for the vast majority of machine learning (ML) algorithms. In the con…
Asynchronous Parallel Stochastic Gradient Descent - A Numeric Core for Scalable Distributed Machine Learning Algorithms
Janis Keuper, Franz-Josef Pfreundt
The implementation of a vast majority of machine learning (ML) algorithms boils down to solving a numerical optimization problem. In this context, Stochastic Gradient Descent (SGD)…