Open Set Domain Adaptation by Extreme Value Theory
This work is significant for researchers and practitioners in domain adaptation, as it tackles the realistic problem of unknown classes in target domains, which existing methods fail to handle effectively.
This paper addresses the open set domain adaptation problem where source and target label spaces only partially overlap. The authors propose an instance-level reweighting strategy combined with Extreme Value Theory to detect unknown target classes and prevent their alignment with the source domain, outperforming state-of-the-art models on conventional domain adaptation datasets.
Common domain adaptation techniques assume that the source domain and the target domain share an identical label space, which is problematic since when target samples are unlabeled we have no knowledge on whether the two domains share the same label space. When this is not the case, the existing methods fail to perform well because the additional unknown classes are also matched with the source domain during adaptation. In this paper, we tackle the open set domain adaptation problem under the assumption that the source and the target label spaces only partially overlap, and the task becomes when the unknown classes exist, how to detect the target unknown classes and avoid aligning them with the source domain. We propose to utilize an instance-level reweighting strategy for domain adaptation where the weights indicate the likelihood of a sample belonging to known classes and to model the tail of the entropy distribution with Extreme Value Theory for unknown class detection. Experiments on conventional domain adaptation datasets show that the proposed method outperforms the state-of-the-art models.