TY  - CONF
AU  - Bojana Gajic
AU  - Ariel Amato
AU  - Ramon Baldrich
AU  - Carlo Gatta
A2  - BMVC
PY  - 2019//
TI  - Bag of Negatives for Siamese Architectures
BT  - 30th British Machine Vision Conference
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/GAB2019b.pdf
N1  - CIC; 600.140; 600.118
ID  - Bojana Gajic2019
ER  -