当前位置: X-MOL 学术Neural Comput. & Applic. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Semi-supervised person re-identification by similarity-embedded cycle GANs
Neural Computing and Applications ( IF 6 ) Pub Date : 2020-03-11 , DOI: 10.1007/s00521-020-04809-7
Xinyu Zhang , Xiao-Yuan Jing , Xiaoke Zhu , Fei Ma

Abstract

Recently, person re-identification (PR-ID) has attracted numerous of research interest because of its broad applications. However, most of the existing PR-ID models always follow the supervised framework, which requires substantial labeled data. In fact, it is often very hard to get enough labeled training samples in many practical application scenarios. To overcome this limitation, some semi-supervised PR-ID methods have been presented more recently. Although some of these semi-supervised models achieve satisfied results, there is still much space to improve. In this paper, we propose a novel semi-supervised PR-ID by similarity-embedded cycle GANs (SECGAN). Our SECGAN model can learn cross-view features with limited labeled data by using cycle GANs. Simultaneously, to further enhance the ability of cycle GANs so that it can extract more discriminative and robust features, similarity metric subnet and specific features extracting subnet are embedded into cycle GANs. Extensive experiments have been conducted on three public PR-ID benchmark datasets, and the experimental results show that our proposed SECGAN approach outperforms several typical supervised methods and the existing state-of-the-art semi-supervised methods including traditional and deep learning semi-supervised methods.



中文翻译:

通过相似嵌入式循环GAN进行半监督人的重新识别

摘要

最近,人员重新识别(PR-ID)由于其广泛的应用而吸引了众多研究兴趣。但是,大多数现有的PR-ID模型始终遵循监督框架,这需要大量标记数据。实际上,在许多实际应用场景中通常很难获得足够的带标签的训练样本。为了克服该限制,最近提出了一些半监督式PR-ID方法。尽管这些半监督模型中的某些模型取得了令人满意的结果,但仍有很大的改进空间。在本文中,我们提出了一种基于相似嵌入式循环GAN(SECGAN)的新型半监督PR-ID。我们的SECGAN模型可以通过使用循环GAN来学习带有有限标记数据的跨视图功能。同时,为了进一步增强循环GAN的能力,以便可以提取出更具区分性和鲁棒性的特征,将相似性度量子网和特定特征提取子网嵌入到循环GAN中。在三个公共PR-ID基准数据集上进行了广泛的实验,实验结果表明,我们提出的SECGAN方法优于几种典型的监督方法和现有的最新半监督方法,包括传统的和深度学习的半监督方法。监督方法。

更新日期:2020-03-12
down
wechat
bug