TY - CONF AU - Felipe Codevilla AU - Antonio Lopez AU - Vladlen Koltun AU - Alexey Dosovitskiy A2 - ECCV PY - 2018// TI - On Offline Evaluation of Vision-based Driving Models T2 - LNCS BT - 15th European Conference on Computer Vision SP - 246 EP - 262 VL - 11219 KW - Autonomous driving KW - deep learning N2 - Autonomous driving models should ideally be evaluated by deployingthem on a fleet of physical vehicles in the real world. Unfortunately, this approach is not practical for the vast majority of researchers. An attractive alternative is to evaluate models offline, on a pre-collected validation dataset with ground truth annotation. In this paper, we investigate the relation between various online and offline metrics for evaluation of autonomous driving models. We find that offline prediction error is not necessarily correlated with driving quality, and two models with identical prediction error can differ dramatically in their driving performance. We show that the correlation of offline evaluation with driving quality can be significantly improved by selecting an appropriate validation dataset andsuitable offline metrics. UR - https://doi.org/10.1007/978-3-030-01267-0_15 L1 - http://refbase.cvc.uab.es/files/CLK2018.pdf N1 - ADAS; 600.124; 600.118 ID - Felipe Codevilla2018 ER -