Improving Cross-View Matching with Self-Supervised Learning
J. Cui (TU Delft - Mechanical Engineering)
Z. Xia – Mentor (TU Delft - Intelligent Vehicles)
J.F.P. Kooij – Mentor (TU Delft - Intelligent Vehicles)
L. Nan – Graduation committee member (TU Delft - Urban Data Science)
More Info
expand_more
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.
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.