Zobrazeno 1 - 10
of 465
pro vyhledávání: '"ESKOFIER, BJÖRN"'
Autor:
Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R., Ndjeuha, Mark A. Turban, Schwinn, Leo, Eskofier, Bjoern
Understanding human attention is crucial for vision science and AI. While many models exist for free-viewing, less is known about task-driven image exploration. To address this, we introduce CapMIT1003, a dataset with captions and click-contingent im
Externí odkaz:
http://arxiv.org/abs/2408.09948
Autor:
Panda, Mahadev Prasad, Tiezzi, Matteo, Vilas, Martina, Roig, Gemma, Eskofier, Bjoern M., Zanca, Dario
We introduce Foveation-based Explanations (FovEx), a novel human-inspired visual explainability (XAI) method for Deep Neural Networks. Our method achieves state-of-the-art performance on both transformer (on 4 out of 5 metrics) and convolutional mode
Externí odkaz:
http://arxiv.org/abs/2408.02123
Mixed-type time series (MTTS) is a bimodal data type that is common in many domains, such as healthcare, finance, environmental monitoring, and social media. It consists of regularly sampled continuous time series and irregularly sampled categorical
Externí odkaz:
http://arxiv.org/abs/2406.15098
Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promising strategies against these attacks, at the expense of a substantial i
Externí odkaz:
http://arxiv.org/abs/2406.13283
Autor:
Stahlke, Maximilian, Yammine, George, Feigl, Tobias, Eskofier, Bjoern M., Mutschler, Christopher
Fingerprint-based localization improves the positioning performance in challenging, non-line-of-sight (NLoS) dominated indoor environments. However, fingerprinting models require an expensive life-cycle management including recording and labeling of
Externí odkaz:
http://arxiv.org/abs/2311.08016
Autor:
Schüßler, Christian, Hoffmann, Marcel, Wirth, Vanessa, Eskofier, Björn, Weyrich, Tim, Stamminger, Marc, Vossiek, Martin
In this work a novel radar simulation concept is introduced that allows to simulate realistic radar data for Range, Doppler, and for arbitrary antenna positions in an efficient way. Further, it makes it possible to automatically annotate the simulate
Externí odkaz:
http://arxiv.org/abs/2305.14176
As the field of deep learning steadily transitions from the realm of academic research to practical application, the significance of self-supervised pretraining methods has become increasingly prominent. These methods, particularly in the image domai
Externí odkaz:
http://arxiv.org/abs/2305.12384
Autor:
Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R., Ndjeuha, Mark A. Turban, Schwinn, Leo, Eskofier, Bjoern
Understanding the mechanisms underlying human attention is a fundamental challenge for both vision science and artificial intelligence. While numerous computational models of free-viewing have been proposed, less is known about the mechanisms underly
Externí odkaz:
http://arxiv.org/abs/2305.12380
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen attacks. Still, t
Externí odkaz:
http://arxiv.org/abs/2305.10388
Autor:
Lüer, Larry, Peters, Marius, Smith, Ana Sunčana, Dorschky, Eva, Eskofier, Bjoern M., Liers, Frauke, Franke, Jörg, Sjarov, Martin, Brossog, Mathias, Guldi, Dirk, Maier, Andreas, Brabec, Christoph J.
The recent successes of emerging photovoltaics (PV) such as organic and perovskite solar cells are largely driven by innovations in material science. However, closing the gap to commercialization still requires significant innovation to match contrad
Externí odkaz:
http://arxiv.org/abs/2305.07573