Cross-dataset tests show BEV segmentation models generalize poorly across datasets and sensor setups, but multi-dataset training improves performance over single-dataset baselines.
Trans- lating images into maps,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
BEVal: A Cross-dataset Evaluation Study of BEV Segmentation Models for Autonomous Driving
Cross-dataset tests show BEV segmentation models generalize poorly across datasets and sensor setups, but multi-dataset training improves performance over single-dataset baselines.