Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Slijepčević, Djordje"'
In this paper we investigate the explainability of transformer models and their plausibility for hate speech and counter speech detection. We compare representatives of four different explainability approaches, i.e., gradient-based, perturbation-base
Externí odkaz:
http://arxiv.org/abs/2407.20274
Autor:
Kirchknopf, Armin, Slijepcevic, Djordje, Wunderlich, Ilkay, Breiter, Michael, Traxler, Johannes, Zeppelzauer, Matthias
Publikováno v:
Proceedings of the Workshop of the Austrian Association for Pattern Recognition 2021
We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to compute at
Externí odkaz:
http://arxiv.org/abs/2211.12108
Autor:
Slijepcevic, Djordje, Horst, Fabian, Simak, Marvin, Lapuschkin, Sebastian, Raberger, Anna-Maria, Samek, Wojciech, Breiteneder, Christian, Schöllhorn, Wolfgang I., Zeppelzauer, Matthias, Horsak, Brian
Publikováno v:
Gait & Posture 97 (Supplement 1) (2022) 252-253
Machine learning (ML) models have proven effective in classifying gait analysis data, e.g., binary classification of young vs. older adults. ML models, however, lack in providing human understandable explanations for their predictions. This "black-bo
Externí odkaz:
http://arxiv.org/abs/2211.17016
Autor:
Horst, Fabian, Slijepcevic, Djordje, Zeppelzauer, Matthias, Raberger, Anna-Maria, Lapuschkin, Sebastian, Samek, Wojciech, Schöllhorn, Wolfgang I., Breiteneder, Christian, Horsak, Brian
Publikováno v:
Gait & Posture 81 (Supplement 1) (2020) 159-160
State-of-the-art machine learning (ML) models are highly effective in classifying gait analysis data, however, they lack in providing explanations for their predictions. This "black-box" characteristic makes it impossible to understand on which input
Externí odkaz:
http://arxiv.org/abs/2211.17015
Autor:
Rind, Alexander, Slijepčević, Djordje, Zeppelzauer, Matthias, Unglaube, Fabian, Kranzl, Andreas, Horsak, Brian
Publikováno v:
Proceedings of the 2022 IEEE Workshop on TRust and EXpertise in Visual Analytics, TREX (2022) 8-15
Three-dimensional clinical gait analysis is essential for selecting optimal treatment interventions for patients with cerebral palsy (CP), but generates a large amount of time series data. For the automated analysis of these data, machine learning ap
Externí odkaz:
http://arxiv.org/abs/2208.05232
Autor:
Schütz, Mina, Boeck, Jaqueline, Liakhovets, Daria, Slijepčević, Djordje, Kirchknopf, Armin, Hecht, Manuel, Bogensperger, Johannes, Schlarb, Sven, Schindler, Alexander, Zeppelzauer, Matthias
Sexism has become an increasingly major problem on social networks during the last years. The first shared task on sEXism Identification in Social neTworks (EXIST) at IberLEF 2021 is an international competition in the field of Natural Language Proce
Externí odkaz:
http://arxiv.org/abs/2106.04908
Social media is accompanied by an increasing proportion of content that provides fake information or misleading content, known as information disorder. In this paper, we study the problem of multimodal fake news detection on a largescale multimodal d
Externí odkaz:
http://arxiv.org/abs/2105.15165
Explainable artificial intelligence is the attempt to elucidate the workings of systems too complex to be directly accessible to human cognition through suitable side-information referred to as "explanations". We present a trainable explanation modul
Externí odkaz:
http://arxiv.org/abs/2105.14824
Autor:
Slijepčević, Djordje, Henzl, Maximilian, Klausner, Lukas Daniel, Dam, Tobias, Kieseberg, Peter, Zeppelzauer, Matthias
Publikováno v:
Comput. Secur. 111, 2021
The protection of private information is a crucial issue in data-driven research and business contexts. Typically, techniques like anonymisation or (selective) deletion are introduced in order to allow data sharing, e. g. in the case of collaborative
Externí odkaz:
http://arxiv.org/abs/2102.04763
Autor:
Slijepcevic, Djordje, Horst, Fabian, Lapuschkin, Sebastian, Raberger, Anna-Maria, Zeppelzauer, Matthias, Samek, Wojciech, Breiteneder, Christian, Schöllhorn, Wolfgang I., Horsak, Brian
Machine learning (ML) is increasingly used to support decision-making in the healthcare sector. While ML approaches provide promising results with regard to their classification performance, most share a central limitation, namely their black-box cha
Externí odkaz:
http://arxiv.org/abs/1912.07737