SOME NOTES ABOUT A RELATIVE ORDER RELATION USED IN UNSUPERVISED DEEP LEARNING

Jahn J (2025)


Publication Type: Journal article

Publication year: 2025

Journal

Book Volume: 7

Pages Range: 141-148

Journal Issue: 2

DOI: 10.23952/jano.7.2025.2.01

Abstract

In the context of unsupervised deep metric learning of image features, Kan, Cen, Mladenovic and He [1] introduced a relative order relation, which is helpful for the comparison of two images in relation to a given special image also called anchor image. This short paper embeds the idea of a relative order relation into a more general mathematical framework. It turns out that this order relation has a strong mathematical structure, which leads to important results on minimality and strong minimality known from vector optimization. Properties of relative order matrices introduced in [1] are also obtained in this general mathematical setting. Among other things, characterizations of strongly minimal objects are given using relative order matrix elements.

Authors with CRIS profile

How to cite

APA:

Jahn, J. (2025). SOME NOTES ABOUT A RELATIVE ORDER RELATION USED IN UNSUPERVISED DEEP LEARNING. Journal of Applied and Numerical Optimization, 7(2), 141-148. https://doi.org/10.23952/jano.7.2025.2.01

MLA:

Jahn, Johannes. "SOME NOTES ABOUT A RELATIVE ORDER RELATION USED IN UNSUPERVISED DEEP LEARNING." Journal of Applied and Numerical Optimization 7.2 (2025): 141-148.

BibTeX: Download