Person re-identification (ReID) aims to match people across multiple non-overlapping video cameras deployed at different locations. To address this challenging problem, many metric learning approaches have been proposed, among which triplet loss is one of the state-of-the-arts. In this work, we explore the margin between positive and negative pairs of triplets and prove that large margin is beneficial. In particular, we propose a novel multi-stage training strategy which learns incremental triplet margin and improves triplet loss effectively. Multiple levels of feature maps are exploited to make the learned features more discriminative. Besides, we introduce global hard identity searching method to sample hard identities when generating a training batch. Extensive experiments on Market-1501, CUHK03, and DukeMTMCreID show that our approach yields a performance boost and outperforms most existing state-of-the-art methods.
翻译:为了解决这一具有挑战性的问题,提出了许多衡量学习方法,其中三重损失是最新艺术之一。在这项工作中,我们探讨了正对对对对对负三重三重三重三重三重三对的差幅,并证明有很大的差幅。特别是,我们提出了一个新的多阶段培训战略,学习增量三重差,并有效地改善三重损失。多层地貌图被利用,使学到的特征更加具有歧视性。此外,我们采用全球硬身份搜索方法,在产生培训批量时抽样硬身份。关于市场1501、CUHK03和DukMTMMCreID的广泛实验表明,我们的方法产生一种业绩提升,并超越了现有最先进的方法。