Training a Siamese architecture for re-identification with a large number of identities is a challenging task due to the difficulty of finding relevant negative samples efficiently. In this work we present Bag of Negatives (BoN), a method for accelerated and improved training of Siamese networks that scales well on datasets with a very large number of identities. BoN is an efficient and loss-independent method, able to select a bag of high quality negatives, based on a novel online hashing strategy.
Cite
@article{arxiv.1908.02391,
title = {Bag of Negatives for Siamese Architectures},
author = {Bojana Gajic and Ariel Amato and Ramon Baldrich and Carlo Gatta},
journal= {arXiv preprint arXiv:1908.02391},
year = {2019}
}