Improving Cross-View Matching with Self-Supervised Learning

Master thesis (2023)

Authors

J. Cui Mechanical Engineering

Contributors

Z. Xia Intelligent Vehicles - Mechanical, Maritime and Materials Engineering (mentor)
J.F.P. Kooij Intelligent Vehicles - Mechanical, Maritime and Materials Engineering (mentor)
L. Nan Urban Data Science - Architecture and the Built Environment (graduation committee member)
Faculty
Mechanical Engineering, Mechanical Engineering
Copyright: © 2023 Jianfeng Cui
More Info
expand_more

Published Date

13-01-2023

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

Mechanical Engineering

Abstract

We explored the possibility of improving cross-view matching performance with self-supervised learning techniques and perform interpretations in terms of the embedding space of image features. The effect of pre-training by contrastive learning is verified quantitatively by experiments, and also exhibited by visualization of the feature space.

Files

Master_thesis_Jianfeng.pdf
(pdf | 7.68 Mb)
Unknown license