[论文解读] Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Yixiao Ge, Dapeng Chen+1 more|arXiv (Cornell University)|Jan 6, 2020

Video Surveillance and Tracking Methods参考文献 50被引用 394

一句话总结

本文提出 Mutual Mean-Teaching (MMT)，一种用于人员重识别（re-ID）的无监督领域自适应框架，通过双网络互教机制，借助在线软标签和离线硬标签来细化嘈杂的伪标签，并使用 soft softmax-triplet loss。

ABSTRACT

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.

研究动机与目标

• 解决基于聚类的无监督领域自适应在人员重识别中的标签噪声问题。
• 利用在线软标签和离线硬标签开发伪标签提炼框架。
• 通过一种新颖的 soft softmax-triplet loss 实现对软三元组标签的训练。
• 证明互助平均教学在标准域自适应基准上能带来显著提升。

提出的方法

• 使用两个协作网络及时间平均模型为对方网络生成可靠的软伪标签。
• 在交替训练过程中，利用离线硬伪标签和在线软伪标签来对目标域伪标签进行细化。
• 引入 soft softmax-triplet loss，使得能够用软伪三元组标签进行学习。
• 在联合优化（两网络）时结合软分类损失和软 softmax-triplet 损失，并选取一个最佳平均模型用于推断。

实验结果

研究问题

• RQ1 用一个互教/师生框架在目标域细化伪标签，是否能提升人员重识别的无监督领域自适应？
• RQ2 软软max-triplet 损失是否能够在软化的细化三元组标签下实现有效学习？
• RQ3 与最先进的基于聚类的 UDA 方法相比，MMT 在标准重识别基准上的性能提升有多大？

主要发现

• MMT 在四个域自适应任务上相较于先前的基于聚类的 UDA 方法实现显著改进：Market-to-Duke、Duke-to-Market、Market-to-MSMT 和 Duke-to-MSMT。
• 该框架在四个任务中如摘要所述的 mAP 提升显著（持续报告为 14.4%、18.2%、13.4%、16.4%）。
• 使用两个时序平均网络来生成软伪标签有助于缓解标签噪声并稳定训练。
• 提出的软 softmax-triplet 损失能够在软性三元组标签下实现有效学习，提升了判别特征的学习效果。
• MMT 在某些任务上达到接近完全监督的性能水平，即使在目标域没有标注且没有后处理步骤如重排序。