activity
20202022
most citedAutoencoder Attractors for Uncertainty Estimation

1 citations · 1 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG20221 cited

Autoencoder Attractors for Uncertainty Estimation

Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter +1

The reliability assessment of a machine learning model's prediction is an important quantity for the deployment in safety critical applications. Not only can it be used to detect n…

cs.CV2022

Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes

Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter +1

Learning on synthetic data and transferring the resulting properties to their real counterparts is an important challenge for reducing costs and increasing safety in machine learni…

cs.CV2021

Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification

Steve Dias Da Cruz, Bertram Taetz, Oliver Wasenmüller +2

Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning…

cs.CV2020

Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function

Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter +1

Images recorded during the lifetime of computer vision based systems undergo a wide range of illumination and environmental conditions affecting the reliability of previously train…

cs.CV2020

SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark

Steve Dias Da Cruz, Oliver Wasenmüller, Hans-Peter Beise +2

We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles, in order to analyze machine learning-based approaches for their generali…