no code implementations • 19 Nov 2023 • Felix Pieper, Konstantin Ditschuneit, Martin Genzel, Alexandra Lindt, Johannes Otterbach
Self-supervised learning for time-series data holds potential similar to that recently unleashed in Natural Language Processing and Computer Vision.
1 code implementation • 14 Apr 2023 • Alexander Koenig, Maximilian Schambach, Johannes Otterbach
The STEGO method for unsupervised semantic segmentation contrastively distills feature correspondences of a DINO-pre-trained Vision Transformer and recently set a new state of the art.
no code implementations • 22 Jun 2021 • Deepthi Sreenivasaiah, Johannes Otterbach, Thomas Wollmann
Active learning helps learning from small amounts of data by suggesting the most promising samples for labeling.
1 code implementation • 30 May 2021 • Samuel von Baußnern, Johannes Otterbach, Adrian Loy, Mathieu Salzmann, Thomas Wollmann
We demonstrate the effectiveness of our approach using an ESPNet trained on the Cityscapes dataset as segmentation model, an affine Normalizing Flow as density estimator and use blue noise to ensure homogeneous sampling.
no code implementations • 8 May 2021 • Johannes Otterbach, Thomas Wollmann
Developing, scaling, and deploying modern Machine Learning solutions remains challenging for small- and middle-sized enterprises (SMEs).