Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centers to produce pseudo labels. In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, for image classification tasks, and demonstrate that CDCL achieves state-of-the-art performance on both datasets.
翻译:未受监督的域适应(UDA)旨在将从全标签源域到不同未标签目标域的知识转让给不同的无标签目标域。大多数现有的UDA方法通过尽量减少不同域间距离来学习域差异特征表现。在这项工作中,我们利用对比式的自我监督学习来调整特征,以减少培训和测试组之间的域差。探索两个域共享的相同类别,我们引入一个简单而有效的框架CDCL(CDCL),以进行域对齐。特别是,鉴于一个域的锁定图像,我们尽可能缩小其距离,从同一类别到跨部样本相对于不同类别样本的距离。由于没有目标标签,我们使用基于集群的办法,在经过仔细初始化的中心制作假标签。此外,我们证明CDCLL(CDCL)是一个总框架,可以适应无数据设置,在培训期间没有源数据,只有最低限度的修改。我们用两种广泛使用的域适应基准(即Office-31和VisDA-2017)进行实验,用于图像分类任务,并证明CDCL(CL)在两个数据设置上达到状态。