Abstract
This paper considers the domain adaptive person re-identification (re-ID) problem: learning a re-ID model from a labeled source domain and an unlabeled target domain. Conventional methods are mainly to reduce feature distribution gap between the source and target domains. However, these studies largely neglect the intra-domain variations in the target domain, which contain critical factors influencing the testing performance on the target domain. In this work, we comprehensively investigate into the intra-domain variations of the target domain and propose to generalize the re-ID model w.r.t three types of the underlying invariance, i.e., exemplar-invariance, camera-invariance and neighborhood-invariance. To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties. The memory allows us to enforce the invariance constraints over global training batch without significantly increasing computation cost. Experiment demonstrates that the three invariance properties and the proposed memory are indispensable towards an effective domain adaptation system. Results on three re-ID domains show that our domain adaptation accuracy outperforms the state of the art by a large margin. Code is available at: https://github.com/zhunzhong07/ECN
Abstract (translated)
本文研究了域自适应人再识别(RE-ID)问题:从标记源域和未标记目标域学习一个RE-ID模型。传统的方法主要是减少源域和目标域之间的特征分布差距。然而,这些研究在很大程度上忽略了目标域的域内变化,这些变化包含了影响目标域测试性能的关键因素。本文对目标域的域内变化进行了全面的研究,提出了将Re-ID模型W.R.T归纳为三种基本不变性,即范数不变性、相机不变性和邻域不变性。为了实现这一目标,引入了一个示例内存来存储目标域的特征并适应这三个不变性。内存允许我们在不显著增加计算成本的情况下对全局训练批执行不变性约束。实验表明,三个不变性和所提出的存储器是一个有效的域自适应系统必不可少的。三个区域的结果表明,我们的区域适应精度在很大程度上优于最新技术。代码可访问:https://github.com/zhunzhong07/ecn
URL
https://arxiv.org/abs/1904.01990