activity
20172022
most citedUnmasking DeepFakes with simple Features

176 citations · 211 across the 16 of their papers we have counts for

collaborators

24 papers

eess.IV20221 cited

Does Medical Imaging learn different Convolution Filters?

Paul Gavrikov, Janis Keuper

Recent work has investigated the distributions of learned convolution filters through a large-scale study containing hundreds of heterogeneous image models. Surprisingly, on averag…

cs.CV20226 cited

Robust Models are less Over-Confident

Julia Grabinski, Paul Gavrikov, Janis Keuper +1

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental c…

cs.CV2022

An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters

Paul Gavrikov, Janis Keuper

We present first empirical results from our ongoing investigation of distribution shifts in image data used for various computer vision tasks. Instead of analyzing the original tra…

cs.CV20218 cited

FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces

Ricard Durall, Jireh Jam, Dominik Strassel +2

Facial image manipulation is a generation task where the output face is shifted towards an intended target direction in terms of facial attribute and styles. Recent works have achi…

cs.CV20211 cited

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…

cs.CV2021

Combining Transformer Generators with Convolutional Discriminators

Ricard Durall, Stanislav Frolov, Jörn Hees +4

Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed wit…