Exploring Training Pair-Generation Strategies for Deep Metric Learning for Floor Plan Retrieval

Master thesis (2024)

Authors

E.F.M. Kuhn Electrical Engineering, Mathematics and Computer Science

Contributors

J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
S. Khademi Building Knowledge - Architecture and the Built Environment (supervisor 1)
C.C.J. van Engelenburg Building Knowledge - Architecture and the Built Environment (supervisor 1)
Catharine Oertel Interactive Intelligence - EEMCS (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2024 Emanuel Kuhn
More Info
expand_more

Published Date

21-02-2024

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Existing content-based image retrieval models work well for natural photos, but not for images of architectural floor plans.
Previous work on floor plan retrieval has focused on graph-based methods, rather than image-based floor plans.
Training a CNN-based representation learning framework on segmented floor plan images with standard image augmentations does not result in semantically meaningful retrievals.
This work shows that a CNN-based representation learning model can learn features for retrieving floor plans that have similar graphs given the right training signal. Two methods were investigated here: GeomPerturb, a data augmentation that perturbs the underlying geometry of a floor plan, and a weakly supervised method with labels based on the graph edit distance between a pair of floor plans. The results show that while GeomPerturb learns representations that are correlated with the floor plan graph, training with GED labels leads to better retrievals both in terms of the floor plan graph and with respect to room shapes.