no code implementations • 21 May 2023 • Toni Albert, Bjoern Eskofier, Dario Zanca
In this paper, we propose a novel auxiliary pretraining method that is based on spatial reasoning.
no code implementations • 21 May 2023 • Dario Zanca, Andrea Zugarini, Simon Dietz, Thomas R. Altstidl, Mark A. Turban Ndjeuha, Leo Schwinn, Bjoern Eskofier
Understanding the mechanisms underlying human attention is a fundamental challenge for both vision science and artificial intelligence.
Ranked #1 on Scanpath prediction on CapMIT1003
no code implementations • 22 Nov 2022 • Leo Schwinn, Doina Precup, Bjoern Eskofier, Dario Zanca
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.
no code implementations • 26 Jul 2022 • Christoffer Loeffler, Kion Fallah, Stefano Fenu, Dario Zanca, Bjoern Eskofier, Christopher John Rozell, Christopher Mutschler
We adapt an entropy-based active learning method with recent work from triplet mining to collect easy-to-answer but still informative annotations from human participants and use them to train a deep convolutional network that generalizes to unseen samples.
1 code implementation • 14 Mar 2022 • Christoffer Loeffler, Wei-Cheng Lai, Bjoern Eskofier, Dario Zanca, Lukas Schmidt, Christopher Mutschler
Explanatory visual interpretation approaches for image, and natural language processing allow domain experts to validate and understand almost any deep learning model.
no code implementations • 29 Sep 2021 • Christoffer Löffler, Wei-Cheng Lai, Lukas M Schmidt, Dario Zanca, Bjoern Eskofier, Christopher Mutschler
(Explanatory) visual interpretation approaches for image and natural language processing allow domain experts to validate and understand almost any deep learning model.
no code implementations • 8 Jul 2021 • Mohamad Wehbi, Tim Hamann, Jens Barth, Bjoern Eskofier
This system is applicable in real-world applications and requires no user-specific training for recognition.
no code implementations • 26 May 2021 • Mohamad Wehbi, Tim Hamann, Jens Barth, Peter Kaempf, Dario Zanca, Bjoern Eskofier
Most online handwriting recognition systems require the use of specific writing surfaces to extract positional data.
no code implementations • 21 May 2021 • Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Bjoern Eskofier
Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community.
1 code implementation • 24 Feb 2021 • Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Bjoern Eskofier
The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications.
1 code implementation • 11 Jan 2021 • An Nguyen, Stefan Foerstel, Thomas Kittler, Andrey Kurzyukov, Leo Schwinn, Dario Zanca, Tobias Hipp, Da Jun Sun, Michael Schrapp, Eva Rothgang, Bjoern Eskofier
The overall framework is currently deployed, learns and evaluates predictive models from terabytes of IoT and enterprise data to actively monitor the customer sentiment for a fleet of thousands of high-end medical devices.
no code implementations • 5 Nov 2020 • Leo Schwinn, An Nguyen, René Raab, Dario Zanca, Bjoern Eskofier, Daniel Tenbrinck, Martin Burger
We empirically show that by incorporating this nonlocal gradient information, we are able to give a more accurate estimation of the global descent direction on noisy and non-convex loss surfaces.
1 code implementation • 21 Oct 2020 • An Nguyen, Wenyu Zhang, Leo Schwinn, Bjoern Eskofier
Process Mining has recently gained popularity in healthcare due to its potential to provide a transparent, objective and data-based view on processes.
1 code implementation • 2 Oct 2020 • An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern Eskofier
To better model the time dependencies between events, we propose a new PBPM technique based on time-aware LSTM (T-LSTM) cells.