mlsanityData to 14 Oct 2026

DINO Pre-training for Vision-based End-to-end Autonomous Driving

arXiv 2407.10803 ↗First posted 15 Jul 2024cs.CV cs.LG cs.ROcited by 2

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners

also in 1 more
Abstract (arXiv)

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).

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 20 of its 29 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

20 of 29 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling3 Jan
  2. 2022Model-Based Imitation Learning for Urban Driving14 Oct
  3. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coach18 Aug

Other references · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  7. 2016End to End Learning for Self-Driving Carscited by 1,009
  8. 2024Large Language Models: A Surveycited by 525
  9. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
  10. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 485
  11. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  12. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 205
5 more
  1. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 169
  2. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  3. 2019Multimodal End-to-End Autonomous Drivingcited by 110
  4. 2022Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretrainingcited by 37
  5. 2019Topological Navigation Graph Frameworkcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Scaling Vision Pre-Training to 4K Resolutioncited by 28
  2. 2025Not Quite Anything: Overcoming SAMs Limitations for 3D Medical Imagingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DriveZero: End-to-End Driving Beyond Human Demonstrations
  2. 2025Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving
  3. 2023Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction
  4. 2026TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
  5. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Web
  6. 2023SSIL: Self-Supervised Imitation Learning for End-to-End Driving
  7. 2026Post-Training in End-to-End Autonomous Driving
  8. 2024An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous Driving