Open Set Domain Adaptation for Image and Action Recognition
This addresses the need for robust domain adaptation in real-world applications where data categories may differ, though it appears incremental as it extends existing methods to handle open set scenarios.
The paper tackles the problem of domain adaptation when target domains contain categories not present in the source domain, proposing an approach for open set domain adaptation that achieves state-of-the-art results on image classification and action recognition datasets.
Since annotating and curating large datasets is very expensive, there is a need to transfer the knowledge from existing annotated datasets to unlabelled data. Data that is relevant for a specific application, however, usually differs from publicly available datasets since it is sampled from a different domain. While domain adaptation methods compensate for such a domain shift, they assume that all categories in the target domain are known and match the categories in the source domain. Since this assumption is violated under real-world conditions, we propose an approach for open set domain adaptation where the target domain contains instances of categories that are not present in the source domain. The proposed approach achieves state-of-the-art results on various datasets for image classification and action recognition. Since the approach can be used for open set and closed set domain adaptation, as well as unsupervised and semi-supervised domain adaptation, it is a versatile tool for many applications.