3 papers
cs.CV2022
How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?
Thomas M. Hehn, Julian F. P. Kooij, Dariu M. Gavrila
Various state-of-the-art self-supervised visual representation learning approaches take advantage of data from multiple sensors by aligning the feature representations across views…
cs.RO2020
Hearing What You Cannot See: Acoustic Vehicle Detection Around Corners
Yannick Schulz, Avinash Kini Mattar, Thomas M. Hehn +1
This work proposes to use passive acoustic perception as an additional sensing modality for intelligent vehicles. We demonstrate that approaching vehicles behind blind corners can…
stat.ML2017
End-to-end Learning of Deterministic Decision Trees
Thomas Hehn, Fred A. Hamprecht
Conventional decision trees have a number of favorable properties, including interpretability, a small computational footprint and the ability to learn from little training data. H…