Learning Non-Metric Visual Similarity for Image Retrieval

Abstract

Measuring visual similarity between two or more instances within a data distribution is a fundamental task in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system. In this work, we explore neural networks models for learning a non-metric similarity function for instance search. We argue that non-metric similarity functions based on neural networks can build a better model of human visual perception than standard metric distances. As our proposed similarity function is differentiable, we explore a real end-to-end trainable approach for image retrieval, i.e. we learn the weights from the input image pixels to the final similarity score. Experimental evaluation shows that non-metric similarity networks are able to learn visual similarities between images and improve performance on top of state-of-the-art image representations, boosting results in standard image retrieval datasets with respect standard metric distances.

Publication DOI: https://doi.org/10.1016/j.imavis.2019.01.001
Divisions: College of Engineering & Physical Sciences > School of Informatics and Digital Engineering > Computer Science
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: © 2019, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Uncontrolled Keywords: Image retrieval,Non-metric learning,Visual similarity,Signal Processing,Computer Vision and Pattern Recognition
Publication ISSN: 1872-8138
Full Text Link:
Related URLs: https://linking ... 262885619300071 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2019-02-10
Accepted Date: 2019-01-19
Authors: Garcia, Noa
Vogiatzis, George (ORCID Profile 0000-0002-3226-0603)

Download

[img]

Version: Draft Version

| Preview

[img]

Version: Accepted Version

License: Creative Commons Attribution Non-commercial No Derivatives

| Preview

Export / Share Citation


Statistics

Additional statistics for this record