Unsupervised similarity learning from compressed representations via Siamese autoencoders

Marek Jakab; Wanda Benesova

doi:10.1117/12.2522920

15 March 2019 Unsupervised similarity learning from compressed representations via Siamese autoencoders

Marek Jakab, Wanda Benesova

Proceedings Volume 11041, Eleventh International Conference on Machine Vision (ICMV 2018); 110412F (2019) https://doi.org/10.1117/12.2522920
Event: Eleventh International Conference on Machine Vision (ICMV 2018), 2018, Munich, Germany

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.

Citation Download Citation

Marek Jakab and Wanda Benesova "Unsupervised similarity learning from compressed representations via Siamese autoencoders", Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110412F (15 March 2019); https://doi.org/10.1117/12.2522920

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available