Abstract
Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are addressed in this paper from the perspective of representation learning. For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains. For the second issue, we exploit the temporal continuity in each camera of target domain to create discriminative information. This is implemented by dynamically generating online triplets within each batch, in order to maximally take advantage of the steadily improved feature representation in training process. Together, the above two methods give rise to a novel unsupervised deep domain adaptation framework for person Re-ID. Experiments and ablation studies on benchmark datasets demonstrate its superiority and interesting properties.
Abstract (translated)
无监督跨域人重新识别(RE ID)面临两个关键问题。一个是源域和目标域之间的数据分布差异,另一个是目标域中缺乏标签信息。本文从表象学习的角度对这些问题进行了探讨。对于第一个问题,我们强调摄像机级子域的存在是人的重新识别的一个独特特征,并开发摄像机感知的域适应,以减少源域和目标域之间以及这些子域之间的差异。对于第二个问题,我们利用目标域中每个摄像头的时间连续性来创建识别信息。这是通过在每个批中动态生成在线三元组来实现的,以最大限度地利用训练过程中稳定改进的特征表示。上述两种方法共同产生了一种新的无监督的人脑深域适应框架,对基准数据集的实验和消融研究证明了其优越性和有趣的特性。
URL
https://arxiv.org/abs/1904.03425