In this article, we focus on the pre-training of visual autonomous driving agents in the context of imitation learning. Current methods often rely on a classification-based pre-training, which we hypothesise to be holding back from extending capabilities of implicit image understanding. We propose pre-training the visual encoder of a driving agent using the self-distillation with no labels (DINO) method, which relies on a self-supervised learning paradigm.% and is trained on an unrelated task. Our experiments in CARLA environment in accordance with the Leaderboard benchmark reveal that the proposed pre-training is more efficient than classification-based pre-training, and is on par with the recently proposed pre-training based on visual place recognition (VPRPre).
@article{arxiv.2407.10803,
title = {DINO Pre-training for Vision-based End-to-end Autonomous Driving},
author = {Shubham Juneja and Povilas Daniušis and Virginijus Marcinkevičius},
journal= {arXiv preprint arXiv:2407.10803},
year = {2025}
}