No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection

no code implementations • 19 Mar 2022 • Mohamed Yousef, Marcel Ackermann, Unmesh Kurup, Tom Bishop

We propose novel architectural modifications to the self-supervised feature learning step, that enable such compact distributions for ID data to be learned.

Out of Distribution (OOD) Detection Self-Supervised Anomaly Detection +2

Explanations can be manipulated and geometry is to blame

2 code implementations • NeurIPS 2019 • Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders, Marcel Ackermann, Klaus-Robert Müller, Pan Kessel

Explanation methods aim to make neural networks more trustworthy and interpretable.

AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark

3 code implementations • 9 Jul 2018 • Sören Becker, Johanna Vielhaben, Marcel Ackermann, Klaus-Robert Müller, Sebastian Lapuschkin, Wojciech Samek

Explainable Artificial Intelligence (XAI) is targeted at understanding how models perform feature selection and derive their classification decisions.

Audio Classification Decision Making +4