Recent works show that mean-teaching is an effective framework for unsupervised domain adaptive person re-identification. However, existing methods perform contrastive learning on selected samples between teacher and student networks, which is sensitive to noises in pseudo labels and neglects the relationship among most samples. Moreover, these methods are not effective in cooperation of different teacher networks. To handle these issues, this paper proposes a Graph Consistency based Mean-Teaching (GCMT) method with constructing the Graph Consistency Constraint (GCC) between teacher and student networks. Specifically, given unlabeled training images, we apply teacher networks to extract corresponding features and further construct a teacher graph for each teacher network to describe the similarity relationships among training images. To boost the representation learning, different teacher graphs are fused to provide the supervise signal for optimizing student networks. GCMT fuses similarity relationships predicted by different teacher networks as supervision and effectively optimizes student networks with more sample relationships involved. Experiments on three datasets, i.e., Market-1501, DukeMTMCreID, and MSMT17, show that proposed GCMT outperforms state-of-the-art methods by clear margin. Specially, GCMT even outperforms the previous method that uses a deeper backbone. Experimental results also show that GCMT can effectively boost the performance with multiple teacher and student networks. Our code is available at https://github.com/liu-xb/GCMT .


翻译:最近的工作表明,平均教学是教师和学生网络之间未经监督的域内适应性适应性人重新定位的有效框架,然而,现有方法对教师和学生网络之间的选定样本进行对比性学习,对假标签中的噪音敏感,忽视大多数样本之间的关系。此外,这些方法在不同教师网络的合作中并不有效。为处理这些问题,本文件建议采用基于图形一致性的平均值教学方法,在教师和学生网络之间构建图形一致性约束度(GCC),具体而言,根据未加标记的培训图像,我们应用教师网络来提取相应的特征,并进一步为每个教师网络绘制教师图表,以描述培训图像之间的类似关系。为了促进代表性学习,将不同的教师图表结合在一起,以提供优化学生网络的监督信号。GCMT将不同教师网络预测的类似性关系作为监督和有效优化学生网络的更多样本关系。在三个数据集上进行实验,即市场1501、DukMMCreID和MSMT17, 显示拟议的GCMT/GMM 系统(GMB-G-GMT) 的深度测试结果也通过GMLA-GMT-GMB-G-GMT-G-GMT-G-S-S-S-S-S-S-S-Serreval-S-S-S-Bral-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-SUIGMT-S-S-F-S-F-F-S-SD-S-S-SD-SD-SD-Frent-S-S-S-S-S-S-S-GMT-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-SD-SD-SD-S-F-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-

0
下载
关闭预览

相关内容

【Google】平滑对抗训练,Smooth Adversarial Training
专知会员服务
48+阅读 · 2020年7月4日
100+篇《自监督学习(Self-Supervised Learning)》论文最新合集
专知会员服务
164+阅读 · 2020年3月18日
Hierarchically Structured Meta-learning
CreateAMind
26+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
27+阅读 · 2019年5月18日
强化学习的Unsupervised Meta-Learning
CreateAMind
17+阅读 · 2019年1月7日
无监督元学习表示学习
CreateAMind
27+阅读 · 2019年1月4日
Unsupervised Learning via Meta-Learning
CreateAMind
42+阅读 · 2019年1月3日
PTGAN for Person Re-Identification
统计学习与视觉计算组
4+阅读 · 2018年9月10日
Arxiv
14+阅读 · 2021年3月10日
VIP会员
相关VIP内容
【Google】平滑对抗训练,Smooth Adversarial Training
专知会员服务
48+阅读 · 2020年7月4日
100+篇《自监督学习(Self-Supervised Learning)》论文最新合集
专知会员服务
164+阅读 · 2020年3月18日
Top
微信扫码咨询专知VIP会员