Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open problem. Unsupervised Domain Adaptation (UDA), especially recently proposed Source-free Domain Adaptation (SFDA), has become a promising technology to address this issue. Nevertheless, existing SFDA methods require that the source domain and target domain share the same label space, consequently being only applicable to the vanilla closed-set setting. In this paper, we take one step further and explore the Source-free Universal Domain Adaptation (SF-UniDA). The goal is to identify "known" data samples under both domain and category shift, and reject those "unknown" data samples (not present in source classes), with only the knowledge from standard pre-trained source model. To this end, we introduce an innovative global and local clustering learning technique (GLC). Specifically, we design a novel, adaptive one-vs-all global clustering algorithm to achieve the distinction across different target classes and introduce a local k-NN clustering strategy to alleviate negative transfer. We examine the superiority of our GLC on multiple benchmarks with different category shift scenarios, including partial-set, open-set, and open-partial-set DA. Remarkably, in the most challenging open-partial-set DA scenario, GLC outperforms UMAD by 14.8\% on the VisDA benchmark. The code is available at https://github.com/ispc-lab/GLC.

翻译：深度神经网络在领域迁移与类别迁移场景下常表现不佳。如何有效升级复用深度神经网络并适配目标任务仍是一个重要的开放问题。无监督领域自适应(UDA)，特别是近期提出的无源领域自适应(SFDA)，已成为解决该问题的潜在技术。然而，现有SFDA方法要求源域与目标域共享相同标签空间，因此仅适用于传统的封闭集设定。本文进一步探索了无源通用域自适应(SF-UniDA)，其目标是在同时存在领域迁移与类别迁移的情况下，仅利用标准预训练源模型的知识，识别"已知"数据样本，并拒绝那些不属于源类别的"未知"数据样本。为此，我们提出了一种创新的全局与局部聚类学习技术(GLC)。具体而言，我们设计了一种自适应一对多全局聚类算法来实现不同目标类别的区分，并引入局部k近邻聚类策略来缓解负迁移。我们在包含部分集、开放集和开放-部分集域自适应等多种类别迁移场景的多个基准上验证了GLC的优越性。值得注意的是，在最具挑战性的开放-部分集域自适应场景中，GLC在VisDA基准上相比UMAD方法提升了14.8%。代码已开源至 https://github.com/ispc-lab/GLC。