Quadruplet-Wise Image Similarity Learning

Marc T. Law, Nicolas Thome, Matthieu Cord; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 249-256

Abstract


This paper introduces a novel similarity learning framework. Working with inequality constraints involving quadruplets of images, our approach aims at efficiently modeling similarity from rich or complex semantic label relationships. From these quadruplet-wise constraints, we propose a similarity learning framework relying on a convex optimization scheme. We then study how our metric learning scheme can exploit specific class relationships, such as class ranking (relative attributes), and class taxonomy. We show that classification using the learned metrics gets improved performance over state-of-the-art methods on several datasets. We also evaluate our approach in a new application to learn similarities between webpage screenshots in a fully unsupervised way.

Related Material


[pdf]
[bibtex]
@InProceedings{Law_2013_ICCV,
author = {Law, Marc T. and Thome, Nicolas and Cord, Matthieu},
title = {Quadruplet-Wise Image Similarity Learning},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}