Contrastive Graph Autoencoder for Shape-based Polygon Retrieval from Large Geometry Datasets
Abstract: Retrieval of polygon geometries with similar shapes from maps is a challenging geographic information task. Existing approaches can not process geometry polygons with complex shapes, (multiple) holes and are sensitive to geometric transformations (e.g., rotation). We propose Contrastive Graph Autoencoder (CGAE), a robust and effective graph representation autoencoder for extracting polygon geometries of similar shapes from real-world building maps based on template queries. By leveraging graph message-passing layers, graph feature augmentation and contrastive learning, the proposed CGAE embeds highly discriminative latent embeddings by reconstructing graph features w.r.t. the graph representations of input polygons, outperforming existing graph-based autoencoders (GAEs) in geometry retrieval of similar polygons. Experimentally, we demonstrate this capability based on template query shapes on real-world datasets and show its high robustness to geometric transformations in contrast to existing GAEs, indicating the strong generalizability and versatility of CGAE, including on complex real-world building footprints.
Submission Length: Regular submission (no more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=QWgUAx7nIi&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DICLR.cc%2F2024%2FConference%2FAuthors%23your-submissions)
Changes Since Last Submission: To TMLR Action Editors,
This paper was previously submitted to ICLR 2024 (OpenReview link attached). The content and format of this submission has been changed to suit TMLR submission guidlines. This submission contains original contributions that do not reuse the authors’ own prior work.
Cheers,
Authors.
Assigned Action Editor: ~Nicolas_THOME2
Submission Number: 2082
Loading