Zobrazeno 1 - 10
of 521
pro vyhledávání: '"Slijepčević, P"'
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:
Slijepcevic, Inigo V., Scaife, Anna M. M., Walmsley, Mike, Bowles, Micah, Wong, O. Ivy, Shabala, Stanislav S., White, Sarah V.
In this work, we apply self-supervised learning with instance differentiation to learn a robust, multi-purpose representation for image analysis of resolved extragalactic continuum images. We train a multi-use model which compresses our unlabelled da
Externí odkaz:
http://arxiv.org/abs/2305.16127
Autor:
Bowles, Micah, Tang, Hongming, Vardoulaki, Eleni, Alexander, Emma L., Luo, Yan, Rudnick, Lawrence, Walmsley, Mike, Porter, Fiona, Scaife, Anna M. M., Slijepcevic, Inigo Val, Adams, Elizabeth A. K., Drabent, Alexander, Dugdale, Thomas, Gürkan, Gülay, Hopkins, Andrew M., Jimenez-Andrade, Eric F., Leahy, Denis A., Norris, Ray P., Rahman, Syed Faisal ur, Ouyang, Xichang, Segal, Gary, Shabala, Stanislav S., Wong, O. Ivy
We present a novel natural language processing (NLP) approach to deriving plain English descriptors for science cases otherwise restricted by obfuscating technical terminology. We address the limitations of common radio galaxy morphology classificati
Externí odkaz:
http://arxiv.org/abs/2304.07171
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:
Bowles, Micah, Tang, Hongming, Vardoulaki, Eleni, Alexander, Emma L., Luo, Yan, Rudnick, Lawrence, Walmsley, Mike, Porter, Fiona, Scaife, Anna M. M., Slijepcevic, Inigo Val, Segal, Gary
We define deriving semantic class targets as a novel multi-modal task. By doing so, we aim to improve classification schemes in the physical sciences which can be severely abstracted and obfuscating. We address this task for upcoming radio astronomy
Externí odkaz:
http://arxiv.org/abs/2210.14760
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
Unknown class distributions in unlabelled astrophysical training data have previously been shown to detrimentally affect model performance due to dataset shift between training and validation sets. For radio galaxy classification, we demonstrate in t
Externí odkaz:
http://arxiv.org/abs/2207.08666
Autor:
Carlo Dindorf, Fabian Horst, Djordje Slijepčević, Bernhard Dumphart, Jonas Dully, Matthias Zeppelzauer, Brian Horsak, Michael Fröhlich
Publikováno v:
Current Issues in Sport Science, Vol 9, Iss 4 (2024)
Biomechanical data collection was largely confined to controlled laboratory setups, relying on marker-based systems or force platforms. However, the emergence of wearable sensors and markerless motion capture has revolutionized this field, enabling d
Externí odkaz:
https://doaj.org/article/6318c743feb04a00b6704788dc5fcf46
