Share Email Print

Proceedings Paper

Unsupervised similarity learning from compressed representations via Siamese autoencoders
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Many domain specific challenges for feature matching and similarity learning in computer vision have been relying on labelled data, either using heuristic or more recent approaches via deep learning. While aiming for precise solutions, we need to process larger number of features which may result in higher computational complexity. This paper proposes a novel method of similarity learning through two-part cost function as it could be done using heuristic approaches in original feature space in an unsupervised manner, while also reducing feature complexity. The features are encoded on the lower dimensionality manifold which preserve original structure of data. This approach takes advantage of siamese networks and autoencoders to obtain compressed features while maintaining same distance properties as in the original feature space. This is done by introducing new loss function with two terms, which aims for good reconstruction as well as learning the similar data point neighborhood from encoded and reconstructed feature space.

Paper Details

Date Published: 15 March 2019
PDF: 7 pages
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110412F (15 March 2019); doi: 10.1117/12.2522920
Show Author Affiliations
Marek Jakab, Slovenska Technicka Univ. (Slovakia)
Wanda Benesova, Slovenska Technicka Univ. (Slovakia)

Published in SPIE Proceedings Vol. 11041:
Eleventh International Conference on Machine Vision (ICMV 2018)
Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?