Learning Non-Metric Visual Similarity for Image Retrieval

Research output: Contribution to journalArticle

View graph of relations Save citation

Authors

Research units

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.

Documents

  • Learning Non-Metric Visual Similarity for Image Retrieval- arXiv

    Rights statement: © 2017 The Authors

    Submitted manuscript, 2 MB, PDF-document

  • Learning Non-Metric Visual Similarity for Image Retrieval

    Rights statement: © 2019, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

    Accepted author manuscript, 3 MB, PDF-document

    Embargo ends: 10/02/20

    Licence: CC BY-NC-ND Show licence

Details

Original languageEnglish
JournalImage and Vision Computing
Early online date10 Feb 2019
DOIs
Publication statusE-pub ahead of print - 10 Feb 2019

Bibliographic note

© 2019, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

    Keywords

  • Image Retrieval, Visual Similarity, Non-Metric Learning

Employable Graduates; Exploitable Research

Copy the text from this field...