Abstract
Person re-identification (Re-ID) across multiple datasets is a challenging yet important task due to the possibly large distinctions between different datasets and the lack of training samples in practical applications. This work proposes a novel unsupervised domain adaption framework which transfers discriminative representations from the labeled source domain (dataset) to the unlabeled target domain (dataset). We propose to formulate the domain adaption task as an one-class classification problem with a novel domain similarity loss. Given the feature map of any image from a backbone network, a novel domain adaptive attention model (DAAM) first automatically learns to separate the feature map of an image to a domain-shared feature (DSH) map and a domain-specific feature (DSP) map simultaneously. Specially, the residual attention mechanism is designed to model DSP feature map for avoiding negative transfer. Then, a DSH branch and a DSP branch are introduced to learn DSH and DSP feature maps respectively. To reduce domain divergence caused by that the source and target datasets are collected from different environments, we force to project the DSH feature maps from different domains to a new nominal domain, and a novel domain similarity loss is proposed based on one-class classification. In addition, a novel unsupervised person Re-ID loss is proposed to take full use of unlabeled target data. Extensive experiments on the Market-1501 and DukeMTMC-reID benchmarks demonstrate state-of-the-art performance of the proposed method. Code will be released to facilitate further studies on the cross-domain person re-identification task.
Abstract (translated)
由于不同数据集之间可能存在很大的差异，并且在实际应用中缺乏培训样本，因此跨多个数据集的人员重新识别（RE ID）是一项具有挑战性的重要任务。本文提出了一种新的无监督域自适应框架，将识别表示从标记源域（dataset）转移到未标记目标域（dataset）。提出了一种新的领域相似性损失的一类分类问题。针对主干网中任意图像的特征映射，提出了一种新的域自适应注意模型（DAAM），该模型首先自动学习将图像的特征映射与域共享特征（DSH）映射和域特定特征（DSP）映射相分离。特别地，为了避免负迁移，设计了基于剩余注意机制的DSP特征映射模型。然后，引入一个DSH分支和一个DSP分支分别学习DSH和DSP特征图。为了减少源数据和目标数据集在不同环境下的域发散，我们强制将不同域的DSH特征映射投影到一个新的名义域，并基于一类分类提出了一种新的域相似性损失。此外，还提出了一种新的无监督人身份证丢失方法，以充分利用未标记的目标数据。在Market-1501和Dukemtmc REID基准上进行的大量实验证明了该方法的最先进性能。将发布代码，以便于进一步研究跨域人员重新识别任务。
URL
https://arxiv.org/abs/1905.10529
