基于可靠性集成的无监督域自适应行人重识别

为了缓解基于伪标签的无监督域自适应行人重识别(UDA person ReID)方法中噪声标签带来的负面影响，提出了一种基于可靠性集成的无监督域自适应行人重识别(UDA-RI)方法。该方法包含渐进式伪标签提炼策略和基于可靠性集成策略两个部分。渐进式伪标签提炼策略通过建立一个不确定性的定量标准来衡量伪标签的可靠性，并采用渐进式采样使得模型得到更加稳定的训练。基于可靠性集成策略考虑了来自不同适应时刻的知识，将来自不同迭代的模型按照可靠性高低分配的权重进行了集成，并将自集成后的两种不同架构的模型再进行集成作为最终推理模型。实验表明，与目前先进的无监督域自适应行人重识别方法相比，UDA-RI方法在Market1501、DukeMTMC-ReID和MSMT17数据集上都取得了优越的性能。

Unsupervised domain adaptive person re-identification based on reliability integration

This paper proposed an unsupervised domain adaptation person re-identification base on reliability integration(UDA-RI) method aimed at alleviating the negative impact of noisy labels in the pseudo-labeling-based unsupervised domain adaptation person re-identification(UDA person ReID). This method consisted of two parts, such as progressive pseudo label refinement strategy and reliability integration strategy. The progressive pseudo label refinement strategy established a quantitative standard for measuring the uncertainty of pseudo labels and adopted gradual sampling to make the model more stable during training. The reliability integration strategy considered knowledge from different adaptation moments, allocated weights according to the reliability levels of models from different iterations, integrated the self-integrated models with different architectures, and used them as the final inference model. Experimental results show that compared with the advanced unsupervised domain adaptation person re-identification methods, the UDA-RI method achieves superior performance on Market1501, DukeMTMC-ReID, and MSMT17 datasets.