mlsanityData to 7 Oct 2026

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

arXiv 2207.08609 ↗First posted 18 Jul 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Representation learning in recent years has been addressed with self-supervised learning methods. The input data is augmented into two distorted views and an encoder learns the representations that are invariant to distortions -- cross-view prediction. Augmentation is one of the key components in cross-view self-supervised learning frameworks to learn visual representations. This paper presents ExAgt, a novel method to include expert knowledge for augmenting traffic scenarios, to improve the learnt representations without any human annotation. The expert-guided augmentations are generated in an automated fashion based on the infrastructure, the interactions between the EGO and the traffic participants and an ideal sensor model. The ExAgt method is applied in two state-of-the-art cross-view prediction methods and the representations learnt are tested in downstream tasks like classification and clustering. Results show that the ExAgt method improves representation learning compared to using only standard augmentations and it provides a better representation space stability. The code is available at https://github.com/lab176344/ExAgt.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

21 of 29 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  6. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  7. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  8. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  9. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  10. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  11. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  12. 2020Rethinking Pre-training and Self-trainingcited by 352
9 more
  1. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  2. 2020CERT: Contrastive Self-supervised Learning for Language Understandingcited by 169
  3. 2021Broaden Your Views for Self-Supervised Video Learningcited by 108
  4. 2021A Survey on Deep-Learning Approaches for Vehicle Trajectory Prediction in Autonomous Drivingcited by 21
  5. 2021What data do we need for training an AV motion planner?cited by 15
  6. 2020Deep Representation Learning and Clustering of Traffic Scenarioscited by 7
  7. 2021Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extractioncited by 4
  8. 2021Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencodercited by 4
  9. 2021Traffic Scenario Clustering by Iterative Optimisation of Self-Supervised Networks Using a Random Forest Activation Pattern Similaritycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddingscited by 0