%0 Conference Proceedings
%T Bag of Negatives for Siamese Architectures
%A Bojana Gajic
%A Ariel Amato
%A Ramon Baldrich
%A Carlo Gatta
%B 30th British Machine Vision Conference
%D 2019
%F Bojana Gajic2019
%O CIC; 600.140; 600.118
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3263), last updated on Tue, 25 Jan 2022 10:39:30 +0100
%X 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.
%U http://refbase.cvc.uab.es/files/GAB2019b.pdf