基于相关性感知和特征重学习的无监督域自适应行人重识别

Unsupervised Domain Adaptive Person Reidentification Based on Relation Awareness and Feature Relearning

不同数据集之间的领域多样性对在一个数据集上训练的行人重识别(Re-ID)模型适应另一个数据集提出了明显的挑战。目前最先进的无监督领域自适应方法是通过对目标领域的聚类算法生成的伪标签进行优化的,但聚类过程中不可避免的标签噪声却被忽略了。这种有噪声的伪标签实质上降低了模型在目标域上进一步改进特征表示的能力。为了解决这一问题,提出一种基于相关性感知注意力(RAA)机制和局部特征重学习(FRL)的相互教学方法进行无监督域自适应行人重识别。在特征提取上,使用多通道关注对应的行人局部特征,利用空间-通道对应关系进行全局和局部特征的判别性细节信息重学习,增强网络的特征表达能力。同时采用相关性感知注意力机制来使两个网络聚焦于不同的特征区域,增强两个网络的差异性和互补性。在公共数据集上对所提方法进行了广泛的实验验证。实验结果表明,所提方法在多个行人重识别任务中都取得了良好的成绩。

Domain diversity between different datasets poses an evident challenge for adapting the person reidentification(ReID)model trained on one dataset to another.Stateoftheart unsupervised domain adaptation methods for person ReID optimize the pseudo labels created by clustering algorithms on the target domain;however,the inevitable label noise caused by the clustering procedure is ignored.Such noisy pseudo labels substantially hinder the model’s ability to further improve feature representations on the target domain.To address this problem,this study proposes a mutual teaching approach for unsupervised domain adaptation of person ReID based on relationaware attention(RAA)and local feature relearning(FRL).For feature extraction,we employ multichannel attention to capture the corresponding local features of a person and use spatialchannel correspondence to relearn discriminative finegrained details of global and local features;thereby,enhancing the network’s feature representation capabilities.We also use RAA to steer the two networks toward different feature regions to enhance their distinctiveness and complementarity.Extensive experiments were conducted on public datasets to validate the proposed method.The experimental results show that the proposed method performs well in multipleperson ReID tasks.