activity
20172023
most citedExploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks

9 citations · 28 across the 10 of their papers we have counts for

collaborators

16 papers

cs.CV2022

Simulating Human Gaze with Neural Visual Attention

Leo Schwinn, Doina Precup, Bjoern Eskofier +1

Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate…

cs.CV2022

Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks

Thomas Altstidl, An Nguyen, Leo Schwinn +4

The widespread success of convolutional neural networks may largely be attributed to their intrinsic property of translation equivariance. However, convolutions are not equivariant…

cs.LG20222 cited

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification

Leo Schwinn, Leon Bungert, An Nguyen +5

The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to e…

cs.CV2021

ICDAR 2021 Competition on On-Line Signature Verification

Ruben Tolosana, Ruben Vera-Rodriguez, Carlos Gonzalez-Garcia +28

This paper describes the experimental framework and results of the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021). The goal of SVC 2021 is to evaluate the limi…

cs.LG2021

Towards an IMU-based Pen Online Handwriting Recognizer

Mohamad Wehbi, Tim Hamann, Jens Barth +3

Most online handwriting recognition systems require the use of specific writing surfaces to extract positional data. In this paper we present a online handwriting recognition syste…

cs.LG20219 cited

Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks

Leo Schwinn, René Raab, An Nguyen +2

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluat…