EUVIMEDEUVIMED entdecken
Crossref

Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering

Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui, Jian Yang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 15883-15895

DOI: 10.1109/tpami.2023.3310791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Shiqi Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 100 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g., due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might not align with the source domain classifier, still forms clear clusters. We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity. We observe that higher affinity should be assigned to reciprocal neighbors. To aggregate information with more context, we consider expanded neighborhoods with small affinity values. Furthermore, we consider the density around each target sample, which can alleviate the negative impact of potential outliers. In the experimental results we verify that the inherent structure of the target features is an important source of information for domain adaptation. We demonstrate that this local structure can be efficiently captured by considering the local neighbors, the reciprocal neighbors, and the expanded neighborhood. Finally, we achieve state-of-the-art performance on several 2D image and 3D point cloud recognition datasets.

Zitieren

APA

Yang, S., Wang, Y., van de Weijer, J., Herranz, L., Jui, S., & Yang, J. (2023). Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 15883-15895. https://doi.org/10.1109/tpami.2023.3310791

Vancouver

Yang S, Wang Y, van de Weijer J, Herranz L, Jui S, Yang J. Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):15883-15895. doi:10.1109/tpami.2023.3310791

BibTeX
@article{Yang2023,
  author = {Yang, Shiqi and Wang, Yaxing and van de Weijer, Joost and Herranz, Luis and Jui, Shangling and Yang, Jian},
  title = {Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {12},
  pages = {15883--15895},
  doi = {10.1109/tpami.2023.3310791}
}
Kostenlos starten →