论文标题
无监督的跨域图像检索的特征表示学习
Feature Representation Learning for Unsupervised Cross-domain Image Retrieval
论文作者
论文摘要
当前有监督的跨域图像检索方法可以实现出色的性能。但是，数据收集和标签的成本施加了在实际应用程序中实践部署的棘手障碍。在本文中，我们研究了无监督的跨域图像检索任务，其中类标签和配对注释不再是训练的先决条件。这是一项极具挑战性的任务，因为没有对内域特征表示学习和跨域对准的监督。我们通过引入以下方式解决这两个挑战：1）一种新的群集对比度学习机制，可帮助提取类别语义感知的特征，以及2）新的距离距离损失，以有效地测量并最大程度地减少域差异，而无需任何外部监督。在办公室和域名数据集上进行的实验始终显示了我们框架优于最先进方法的出色图像检索精度。可以在https://github.com/conghuihu/ucdir上找到我们的源代码。
Current supervised cross-domain image retrieval methods can achieve excellent performance. However, the cost of data collection and labeling imposes an intractable barrier to practical deployment in real applications. In this paper, we investigate the unsupervised cross-domain image retrieval task, where class labels and pairing annotations are no longer a prerequisite for training. This is an extremely challenging task because there is no supervision for both in-domain feature representation learning and cross-domain alignment. We address both challenges by introducing: 1) a new cluster-wise contrastive learning mechanism to help extract class semantic-aware features, and 2) a novel distance-of-distance loss to effectively measure and minimize the domain discrepancy without any external supervision. Experiments on the Office-Home and DomainNet datasets consistently show the superior image retrieval accuracies of our framework over state-of-the-art approaches. Our source code can be found at https://github.com/conghuihu/UCDIR.
