当前位置: X-MOL 学术Comput. Intell. Neurosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Stable Median Centre Clustering for Unsupervised Domain Adaptation Person Re-Identification
Computational Intelligence and Neuroscience Pub Date : 2021-07-22 , DOI: 10.1155/2021/2883559
Jifeng Guo 1 , Wenbo Sun 1 , Zhiqi Pang 1 , Yuxiao Fei 1 , Yu Chen 1
Affiliation  

The current unsupervised domain adaptation person re-identification (re-ID) method aims to solve the domain shift problem and applies prior knowledge learned from labelled data in the source domain to unlabelled data in the target domain for person re-ID. At present, the unsupervised domain adaptation person re-ID method based on pseudolabels has obtained state-of-the-art performance. This method obtains pseudolabels via a clustering algorithm and uses these pseudolabels to optimize a CNN model. Although it achieves optimal performance, the model cannot be further optimized due to the existence of noisy labels in the clustering process. In this paper, we propose a stable median centre clustering (SMCC) for the unsupervised domain adaptation person re-ID method. SMCC adaptively mines credible samples for optimization purposes and reduces the impact of label noise and outliers on training to improve the performance of the resulting model. In particular, we use the intracluster distance confidence measure of the sample and its K-reciprocal nearest neighbour cluster proportion in the clustering process to select credible samples and assign different weights according to the intracluster sample distance confidence of samples to measure the distances between different clusters, thereby making the clustering results more robust. The experiments show that our SMCC method can select credible and stable samples for training and improve performance of the unsupervised domain adaptation model. Our code is available at https://github.com/sunburst792/SMCC-method/tree/master.

中文翻译:

无监督域适应人重识别的稳定中值中心聚类

当前的无监督域自适应行人重识别(re-ID)方法旨在解决域转移问题,并将从源域中标记数据学习到的先验知识应用到目标域中的未标记数据中进行行人重识别。目前,基于伪标签的无监督域自适应行人重识别方法已经获得了最先进的性能。该方法通过聚类算法获得伪标签,并使用这些伪标签来优化 CNN 模型。虽然它达到了最佳性能,但由于聚类过程中存在噪声标签,模型无法进一步优化。在本文中,我们为无监督域自适应行人 re-ID 方法提出了一种稳定的中值中心聚类(SMCC)。SMCC 自适应地挖掘可信样本以进行优化,并减少标签噪声和异常值对训练的影响,以提高结果模型的性能。特别地,我们使用样本的簇内距离置信度及其K- reciprocal最近邻簇比例在聚类过程中选择可信样本,并根据样本的簇内样本距离置信度分配不同的权重来衡量不同簇之间的距离,从而使聚类结果更加稳健。实验表明,我们的 SMCC 方法可以选择可信且稳定的样本进行训练,并提高无监督域自适应模型的性能。我们的代码可在 https://github.com/sunburst792/SMCC-method/tree/master 获得。
更新日期:2021-07-22
down
wechat
bug