3 papers
eess.AS2020
The Impact of Label Noise on a Music Tagger
Katharina Prinz, Arthur Flexer, Gerhard Widmer
We explore how much can be learned from noisy labels in audio music tagging. Our experiments show that carefully annotated labels result in highest figures of merit, but even high…
eess.AS2020
End-to-End Adversarial White Box Attacks on Music Instrument Classification
Katharina Prinz, Arthur Flexer
Small adversarial perturbations of input data are able to drastically change performance of machine learning systems, thereby challenging the validity of such systems. We present t…
cs.LG2019
scikit-hubness: Hubness Reduction and Approximate Neighbor Search
Roman Feldbauer, Thomas Rattei, Arthur Flexer
This paper introduces scikit-hubness, a Python package for efficient nearest neighbor search in high-dimensional spaces. Hubness is an aspect of the curse of dimensionality, and is…