-
Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognition
Hoedt, K., Flexer, A. & Widmer, G., 2025, Proceedings of the 22nd Sound and Music Computing Conference 2025 (SMC-25). 1 Aufl. 8 S.Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung
Open Access -
Towards Understanding Deep Learning and its Vulnerabilities in Music Information Research
Hoedt, K., 2025, 180 S.Publikation: Abschlussarbeiten › Dissertation
-
Constructing Adversarial Examples to Investigate The Plausibility of Explanations in Deep Audio And Image Classifiers
Hoedt, K., Praher, V., Flexer, A. & Widmer, G., Mai 2023, in: Neural Computing and Applications. 35, 14, S. 10011-10029 19 S.Publikation: Beitrag in Fachzeitschrift › Artikel › Begutachtung
Open Access -
Concept-Based Techniques for Musicologist-Friendly Explanations In Deep Music Classifiers
Foscarin, F., Hoedt, K., Praher, V., Flexer, A. & Widmer, G., Dez. 2022, Proceedings of the 23rd InternationalSociety for Music Information Retrieval Conference (ISMIR 2022). 8 S.Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung
-
Defending a Music Recommender Against Hubness-Based Adversarial Attacks
Hoedt, K., Flexer, A. & Widmer, G., Juni 2022, Proceedings of the Sound and Music Computing Conference (SMC 2022). Michon, R., Pottier, L. & Orlarey, Y. (Hrsg.). S. 389-394 6 S. (Proceedings of the Sound and Music Computing Conferences).Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung
Katharina Hoedt
DI Dr., BSc
- E-Mailkatharina.hoedtjkuat