Deep Metric Learning Using Triplet Network. Hoffer, E. & Ailon, N.
Paper abstract bibtex Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.
@article{hofferDeepMetricLearning2014,
archivePrefix = {arXiv},
eprinttype = {arxiv},
eprint = {1412.6622},
primaryClass = {cs, stat},
title = {Deep Metric Learning Using {{Triplet}} Network},
url = {http://arxiv.org/abs/1412.6622},
abstract = {Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.},
urldate = {2019-01-05},
date = {2014-12-20},
keywords = {Computer Science - Computer Vision and Pattern Recognition,Statistics - Machine Learning,Computer Science - Machine Learning},
author = {Hoffer, Elad and Ailon, Nir},
file = {/home/dimitri/Nextcloud/Zotero/storage/Z66BDQLS/Hoffer and Ailon - 2014 - Deep metric learning using Triplet network.pdf;/home/dimitri/Nextcloud/Zotero/storage/NRZ8EIN8/1412.html}
}