Source-free unsupervised domain adaptation (SFUDA) aims to learn a target domain model using unlabeled target data and the knowledge of a well-trained source domain model. Most previous SFUDA works focus on inferring semantics of target data based on the source knowledge. Without measuring the transferability of the source knowledge, these methods insufficiently exploit the source knowledge, and fail to identify the reliability of the inferred target semantics. However, existing transferability measurements require either source data or target labels, which are infeasible in SFUDA. To this end, firstly, we propose a novel Uncertainty-induced Transferability Representation (UTR), which leverages uncertainty as the tool to analyse the channel-wise transferability of the source encoder in the absence of the source data and target labels. The domain-level UTR unravels how transferable the encoder channels are to the target domain and the instance-level UTR characterizes the reliability of the inferred target semantics. Secondly, based on the UTR, we propose a novel Calibrated Adaption Framework (CAF) for SFUDA, including i)the source knowledge calibration module that guides the target model to learn the transferable source knowledge and discard the non-transferable one, and ii)the target semantics calibration module that calibrates the unreliable semantics. With the help of the calibrated source knowledge and the target semantics, the model adapts to the target domain safely and ultimately better. We verified the effectiveness of our method using experimental results and demonstrated that the proposed method achieves state-of-the-art performances on the three SFUDA benchmarks. Code is available at https://github.com/SPIresearch/UTR.
翻译:无源且不受监督的域适应(SFUDA)旨在学习一个目标域模型,使用未贴标签的目标数据和训练有素的来源域模型的知识。多数前的SFUDA工作的重点是根据源知识推断目标数据的语义。这些方法在不测量源知识的可转让性的情况下,没有充分利用源知识的可转让性,也没有确定推断目标语义的可靠性。然而,现有的可转让性测量要求源数据或目标标签,在SFUDA中是行不通的。为此目的,首先,我们提出了一个新的“不确定性诱导的源域域图”(UTR),它利用不确定性作为工具,分析源数据和目标标值的可转让性标值的可转让性。 域级UTR揭示了将编码渠道转移到目标域域的可靠性,而实例级UTRT是推断目标语义的可靠性。基于UTRFI,我们提议在SFUDA、SFODA、SLO、SLOFA、SLO、SLA、SLA、SLA、SLA、SLA、SLA、SLA、S、SU、SLA、SLA、S、S、SLA、SLA、S、SULA、SLA、S、S、S、S、SLA、LA、LA、LA、S、LA、S、S、LA、S、LA、LA、S、S、S、S、S、A、A、A、A、A、LA、LA、A、LO、LO、LO、A、A、A、A、A、A、LO、A、A、LO、A、A、A、A、A、A、A、A、A、A、A、L、L、L、L、A、A、A、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、L、LO、L、L、