论文标题
相互卑鄙的教学：伪标签的炼油厂，用于对人重新识别的无监督域的适应
Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
论文作者
论文摘要
人重新识别（RE-ID）旨在识别在不同相机中的同一人的图像。但是，不同数据集之间的域多样性提出了一个明显的挑战，即将在一个数据集中训练的重新ID模型适应另一个数据集。人重新ID的最新无监督域的适应方法通过用在目标域上的聚类算法创建的伪标签来优化源域，从源域转移了学识。尽管他们实现了最新的表演，但忽略了由聚类程序引起的不可避免的标签噪声。这种嘈杂的伪标签极大地阻碍了该模型的能力进一步改善目标域上的特征表示。为了减轻嘈杂的伪标签的影响，我们建议通过提议一个无监督的框架，相互含义的教学（MMT）轻轻完善目标领域中的伪标签，以通过离线型号的硬伪伪贴标标签和在线式软pseudatient ofertivatient and and Anterage toble and An an an Ch An On an Ch an an Ch An On an an Charn and Anter On an an C An an an Ch An On Chor Anter On Chore Anter-Pseefline toble tocal intain域中学习更好的特征。此外，普遍的做法是共同采用分类损失和三胞胎损失，共同在个人重新ID模型中实现最佳性能。但是，传统的三重态损失无法与软化标签一起使用。为了解决这个问题，提出了一种新型的软智能损失，以支持使用软伪三重列标签学习以实现最佳域的适应性性能。拟议的MMT框架在市场到duke，杜克到市场，市场对MSMT和Duke-to-MSMT无监督的域适应任务上，在市场到杜克，杜克到杜克，杜克至市场上的地图上实现了相当大的改善。代码可在https://github.com/yxgeee/mmt上找到。
Person re-identification (re-ID) aims at identifying the same persons' images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to another one. State-of-the-art unsupervised domain adaptation methods for person re-ID transferred the learned knowledge from the source domain by optimizing with pseudo labels created by clustering algorithms on the target domain. Although they achieved state-of-the-art performances, the inevitable label noise caused by the clustering procedure was ignored. Such noisy pseudo labels substantially hinders the model's capability on further improving feature representations on the target domain. In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner. In addition, the common practice is to adopt both the classification loss and the triplet loss jointly for achieving optimal performances in person re-ID models. However, conventional triplet loss cannot work with softly refined labels. To solve this problem, a novel soft softmax-triplet loss is proposed to support learning with soft pseudo triplet labels for achieving the optimal domain adaptation performance. The proposed MMT framework achieves considerable improvements of 14.4%, 18.2%, 13.1% and 16.4% mAP on Market-to-Duke, Duke-to-Market, Market-to-MSMT and Duke-to-MSMT unsupervised domain adaptation tasks. Code is available at https://github.com/yxgeee/MMT.
