English

Bag of Negatives for Siamese Architectures

Computer Vision and Pattern Recognition 2019-08-08 v1

Abstract

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}
}

Comments

accepted for BMVC2019

R2 v1 2026-06-23T10:41:33.191Z