3 citations · 4 across the 6 of their papers we have counts for
6 papers
The Data Manifold under the Microscope
Marios Koulakis, Constantin Seibold
A significant gap exists between theory and practice in deep learning. Generalization and approximation error bounds are often derived for simplified models or are too loose to be…
Domain-independent detection of known anomalies
Jonas Bühler, Jonas Fehrenbach, Lucas Steinmann +2
One persistent obstacle in industrial quality inspection is the detection of anomalies. In real-world use cases, two problems must be addressed: anomalous data is sparse and the sa…
Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
M. Saquib Sarfraz, Mei-Yen Chen, Lukas Layer +2
The current state of machine learning scholarship in Timeseries Anomaly Detection (TAD) is plagued by the persistent use of flawed evaluation metrics, inconsistent benchmarking pra…
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates
Alina Roitberg, Kunyu Peng, David Schneider +4
Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unfore…
Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
M. Saquib Sarfraz, Marios Koulakis, Constantin Seibold +1
Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning. We introduce a novel method based on a hierarchy built on 1…
Affect-DML: Context-Aware One-Shot Recognition of Human Affect using Deep Metric Learning
Kunyu Peng, Alina Roitberg, David Schneider +3
Human affect recognition is a well-established research area with numerous applications, e.g., in psychological care, but existing methods assume that all emotions-of-interest are…