arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.04662cs.CV
收藏

双簇对比学习用于目标重识别

Dual Cluster Contrastive learning for Object Re-Identification

Hantao Yao, Changsheng Xu

AI总结:

双簇对比学习框架DCC通过结合个体和聚类中心更新机制,提升目标重识别的性能。

摘要:

最近,通过计算个体特征与集群记忆之间的对比损失,集群对比学习已被证明在目标重识别(ReID)中是有效的。然而,现有方法使用个体特征来动量更新集群记忆时,会在训练示例上产生波动,特别是对于离群样本。不同于基于个体的更新机制,基于聚类中心的更新机制通过应用每个聚类的平均特征来更新集群记忆,可以减少单个样本的影响。因此,我们将在统一的集群对比框架中将基于个体的更新和基于聚类中心的更新机制结合起来,命名为双簇对比框架(DCC),该框架维护两种类型的记忆银行:个体和聚类中心记忆银行。值得注意的是,个体集群记忆每次只考虑一个个体进行更新。聚类中心集群记忆则应用每个聚类的平均特征来更新相应的集群记忆。在优化过程中,除了每个记忆的valina对比损失外,还应用了跨视图一致性约束,以交换两种记忆的益处,从而生成具有判别性的目标重识别描述。请注意,DCC可以通过使用真实标签或生成的伪标签轻松应用于无监督或有监督的目标重识别。在三个基准测试(例如Market-1501、MSMT17和VeRi-776)上,针对有监督的目标重识别和无监督的目标重识别进行了大量实验,证明了所提DCC的优越性。

英文摘要:

Recently, cluster contrastive learning has been proven effective for object ReID by computing the contrastive loss between the individual features and the cluster memory. However, existing methods that use the individual features to momentum update the cluster memory will fluctuate over the training examples, especially for the outlier samples. Unlike the individual-based updating mechanism, the centroid-based updating mechanism that applies the mean feature of each cluster to update the cluster memory can reduce the impact of individual samples. Therefore, we formulate the individual-based updating and centroid-based updating mechanisms in a unified cluster contrastive framework, named Dual Cluster Contrastive framework (DCC), which maintains two types of memory banks: individual and centroid cluster memory banks. Significantly, the individual cluster memory considers just one individual at a time to take a single step for updating. The centroid cluster memory applies the mean feature of each cluster to update the corresponding cluster memory. During optimization, besides the vallina contrastive loss of each memory, a cross-view consistency constraint is applied to exchange the benefits of two memories for generating a discriminative description for the object ReID. Note that DCC can be easily applied for unsupervised or supervised object ReID by using ground-truth labels or the generated pseudo-labels. Extensive experiments on three benchmarks, \emph{e.g.,} Market-1501, MSMT17, and VeRi-776, under \textbf{supervised Object ReID} and \textbf{unsupervised Object ReID} demonstrate the superiority of the proposed DCC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑