A self-supervised JEPA model on nuPlan data uses temporal prediction error to score driving scenario complexity without labels, assigning higher scores to turns and pedestrian interactions and achieving AP 0.512 in anomaly detection.
arXiv preprint arXiv:2502.05677 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Zero-Label Driving Scenario Complexity Detection via Joint Embedding Predictive Architecture
A self-supervised JEPA model on nuPlan data uses temporal prediction error to score driving scenario complexity without labels, assigning higher scores to turns and pedestrian interactions and achieving AP 0.512 in anomaly detection.