MapGCLR applies geospatial contrastive learning on multi-traversal overlapping data to enhance BEV representations for vectorized online HD map construction and reports better performance than supervised baselines in a semi-supervised setup.
Emerging properties in self-supervised vision transformers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction
MapGCLR applies geospatial contrastive learning on multi-traversal overlapping data to enhance BEV representations for vectorized online HD map construction and reports better performance than supervised baselines in a semi-supervised setup.