Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification
复制标题
DOI：
10.1109/cvpr.2018.00242
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Jingya Wang;Xiatian Zhu;S. Gong;Wei Li-
中科院分区：
文献类型：
--
作者：
Jingya Wang;Xiatian Zhu;S. Gong;Wei Li-
大多数现有的人重新识别（re-id）方法需要从每个单个相机对的单独的大型成对标记训练数据集进行监督模型学习。这大大限制了它们在现实世界的大规模部署中的可扩展性和可用性，需要在许多相机视图中执行re-id。为了解决这个可扩展性问题，我们开发了一种新的深度学习方法，用于将现有数据集的标记信息转移到一个新的看不见的（未标记的）目标域，以进行人员重新识别，而无需在目标域中进行任何监督学习。具体来说，我们引入了一种可转移的联合属性-身份深度学习（TJ-AIDL），用于同时学习可转移到任何新的（看不见的）目标域的属性语义和身份区分特征表示空间，以进行重新识别任务，而无需从目标域收集新的标记训练数据（即目标域中的无监督学习）。广泛的比较评估验证了这种新的TJ-AIDL模型在VIPeR，PRID，Market-1501和DukeMTMC-ReID等四个具有挑战性的基准上的无监督人员re-id的优越性。
Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in real-world large scale deployments with the need for performing re-id across many camera views. To address this scalability problem, we develop a novel deep learning method for transferring the labelled information of an existing dataset to a new unseen (unlabelled) target domain for person re-id without any supervised learning in the target domain. Specifically, we introduce an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identity-discriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain). Extensive comparative evaluations validate the superiority of this new TJ-AIDL model for unsupervised person re-id over a wide range of state-of-the-art methods on four challenging benchmarks including VIPeR, PRID, Market-1501, and DukeMTMC-ReID.