Abstract
Domain adaptation has attracted a great deal of attention in the machine learning community, but it requires access to source data, which often raises concerns about data privacy. We are thus motivated to address these issues and propose a simple yet efficient method. This work treats domain adaptation as an unsupervised clustering problem and trains the target model without access to the source data. Specifically, we propose a loss function called contrast and clustering (CaC), where a positive pair term pulls neighbors belonging to the same class together in the feature space to form clusters, while a negative pair term pushes samples of different classes apart. In addition, extended neighbors are taken into account by querying the nearest neighbor indexes in the memory bank to mine for more valuable negative pairs. Extensive experiments on three common benchmarks, VisDA, Office-Home and Office-31, demonstrate that our method achieves state-of-the-art performance. The code will be made publicly available at this https URL.
Abstract (translated)
域转换在机器学习社区中引起了很多关注,但它需要访问源数据,这常常引起数据隐私方面的疑虑。因此我们有动力解决这些问题并提出一个简单但高效的方法。这项工作将域转换视为无监督聚类问题,并训练目标模型在没有访问源数据的情况下。具体来说,我们提议一个损失函数,称为对比和聚类(CaC),其中正对项将同一类邻居在特征空间中聚集在一起,形成簇,而负对项将不同类样本之间的距离拉大。此外,我们还将扩展邻居考虑在内,通过查询内存 bank中的最近邻居索引来挖掘更有价值的负对项。在三个常见的基准测试中,进行了广泛的实验,包括 VisDA、Office-Home 和 Office-31,证明了我们的方法取得了最先进的性能。代码将在 this https URL 上公开可用。
URL
https://arxiv.org/abs/2301.13428