Towards Map-Based Validation of Semantic Segmentation Masks

Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness. We propose to validate machine learning models for self-driving vehicles not only with given ground truth labels, but also with additional a-priori knowledge. In particular, we suggest to validate the drivable area in semantic segmentation masks using given street map data. We present first results, which indicate that prediction errors can be uncovered by map-based validation.

  • Published in:
    AIAD Workshop at ICML Workshop on AI for Autonomous Driving (AIAD) at the International Conference on Machine Learning (ICML)
  • Type:
    Inproceedings
  • Authors:
    L. von Rüden, T. Wirtz, F. Hueger, J. D. Schneider, C. Bauckhage
  • Year:
    2020

Citation information

L. von Rüden, T. Wirtz, F. Hueger, J. D. Schneider, C. Bauckhage: Towards Map-Based Validation of Semantic Segmentation Masks, Workshop on AI for Autonomous Driving (AIAD) at the International Conference on Machine Learning (ICML), AIAD Workshop at ICML, 2020, https://doi.org/10.48550/arXiv.2011.08008, Rueden.etal.2020a,