ExAgt: Expert-guided Augmentation for Representation Learning of Traffic Scenarios

1 code implementation • 18 Jul 2022 • Lakshman Balasubramanian, Jonas Wurst, Robin Egolf, Michael Botsch, Wolfgang Utschick, Ke Deng

The input data is augmented into two distorted views and an encoder learns the representations that are invariant to distortions -- cross-view prediction.

Representation Learning Self-Supervised Learning