Timezone: »

Confidence Score for Source-Free Unsupervised Domain Adaptation
Jonghyun Lee · Dahuin Jung · Junho Yim · Sungroh Yoon

Tue Jul 19 11:35 AM -- 11:40 AM (PDT) @ Room 301 - 303

Source-free unsupervised domain adaptation (SFUDA) aims to obtain high performance in the unlabeled target domain using the pre-trained source model, not the source data.Existing SFUDA methods assign the same importance to all target samples, which is vulnerable to incorrect pseudo-labels.To differentiate between sample importance, in this study, we propose a novel sample-wise confidence score, the Joint Model-Data Structure (JMDS) score for SFUDA.Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge.We then propose a Confidence score Weighting Adaptation using the JMDS (CoWA-JMDS) framework for SFUDA.CoWA-JMDS consists of the JMDS scores as sample weights and weight Mixup that is our proposed variant of Mixup.Weight Mixup promotes the model make more use of the target domain knowledge.The experimental results show that the JMDS score outperforms the existing confidence scores.Moreover, CoWA-JMDS achieves state-of-the-art performance on various SFUDA scenarios: closed, open, and partial-set scenarios.

Author Information

Jonghyun Lee (Seoul National University)
Dahuin Jung (Seoul National University)
Junho Yim (AIRS Company, Hyundai Motor Group)
Sungroh Yoon (Seoul National University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors