EUVIMEDEUVIMED entdecken
Crossref

WDAN: A Weighted Discriminative Adversarial Network With Dual Classifiers for Fine-Grained Open-Set Domain Adaptation

Jing Li, Liu Yang, Qilong Wang, Qinghua Hu

IEEE Transactions on Circuits and Systems for Video Technology · 2023-09 · 33 (9) · 5133-5147

DOI: 10.1109/tcsvt.2023.3249200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-09. Verfasst von Jing Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep neural networks usually depend on substantial labeled data and suffer from poor generalization to new domains. Domain adaptation can be used to resolve these issues, using a classifier trained with a label-rich source and transferred to a label-scarce target domain. Traditional domain adaptation adopts the close-set assumption that both domains share the same classes. However, real-world applications operate in an open-set scenario where target domains have private categories. This aspect is considered by open-set domain adaptation (OSDA). Nevertheless, current OSDA benchmarks lack clear definitions of semantic classes that are at the core of the open-set concept. In this study, we propose fine-grained visual categorization (FGVC) datasets containing specific descriptions of semantic classes as a solution, introducing the new setting named fine-grained OSDA. Owing to the entanglement among FGVC, unknown class recognition, and domain adaptation, fine-grained OSDA is a challenging task. For this reason, we designed a weighted discriminative adversarial network with dual classifiers (WDAN). It utilizes a selective transformer encoder with overlapping patches and supervised contrastive learning to extract features suitable for FGVC, adversarial training with domain-specific discriminative information to recognize target-private classes, and a weighted conditional domain discriminator to learn domain-invariant features for domain adaptation. Extensive experiments on five benchmarks, including one newly built, demonstrated that WDAN outperforms state-of-the-art methods. This work fills the existing gap in benchmarks for fine-grained OSDA, promoting future developments of real-world applications.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, J., Yang, L., Wang, Q., & Hu, Q. (2023). WDAN: A Weighted Discriminative Adversarial Network With Dual Classifiers for Fine-Grained Open-Set Domain Adaptation. IEEE Transactions on Circuits and Systems for Video Technology, 33(9), 5133-5147. https://doi.org/10.1109/tcsvt.2023.3249200

Vancouver

Li J, Yang L, Wang Q, Hu Q. WDAN: A Weighted Discriminative Adversarial Network With Dual Classifiers for Fine-Grained Open-Set Domain Adaptation. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(9):5133-5147. doi:10.1109/tcsvt.2023.3249200

BibTeX
@article{Li2023,
  author = {Li, Jing and Yang, Liu and Wang, Qilong and Hu, Qinghua},
  title = {WDAN: A Weighted Discriminative Adversarial Network With Dual Classifiers for Fine-Grained Open-Set Domain Adaptation},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {9},
  pages = {5133--5147},
  doi = {10.1109/tcsvt.2023.3249200}
}
Kostenlos starten →