Bag of Negatives for Siamese Architectures
This addresses a bottleneck in re-identification for computer vision applications, but appears incremental as it builds on existing Siamese architectures.
The paper tackles the challenge of efficiently finding relevant negative samples for training Siamese networks in re-identification tasks with many identities, presenting Bag of Negatives (BoN) as a method that accelerates and improves training while scaling well on large datasets.
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.