MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction

TL;DR

MapGCLR introduces a geospatial contrastive learning method for online vectorized HD map construction, reducing annotation needs and improving map perception accuracy through semi-supervised training with overlapping BEV features.

Contribution

It proposes a novel geospatial contrastive loss and dataset splitting method to enhance BEV feature representation in online HD map construction.

Findings

Outperforms supervised baseline in map perception tasks

Improves segmentation quality in PCA visualization of BEV features

Enables semi-supervised training with less labeled data

Abstract

Autonomous vehicles rely on map information to understand the world around them. However, the creation and maintenance of offline high-definition (HD) maps remains costly. A more scalable alternative lies in online HD map construction, which only requires map annotations at training time. To further reduce the need for annotating vast training labels, self-supervised training provides an alternative. This work focuses on improving the latent birds-eye-view (BEV) feature grid representation within a vectorized online HD map construction model by enforcing geospatial consistency between overlapping BEV feature grids as part of a contrastive loss function. To ensure geospatial overlap for contrastive pairs, we introduce an approach to analyze the overlap between traversals within a given dataset and generate subsidiary dataset splits following adjustable multi-traversal requirements. We train the same model supervised using a reduced set of single-traversal labeled data and self-supervised on a broader unlabeled set of data following our multi-traversal requirements, effectively implementing a semi-supervised approach. Our approach outperforms the supervised baseline across the board, both quantitatively in terms of the downstream tasks vectorized map perception performance and qualitatively in terms of segmentation in the principal component analysis (PCA) visualization of the BEV feature space.