EUVIMEDEUVIMED entdecken
Crossref

Revisiting Source-Free Domain Adaptation Object Detection in Thresholds

Yuchen Dong, Chengeyang Li, Yongqiang Xie, Zhongbo Li

IEEE Transactions on Multimedia · 2025 · 27 · 6976-6985

DOI: 10.1109/tmm.2025.3590905 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2025. Verfasst von Yuchen Dong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Source-free domain adaptive object detection (SFOD) aims to transfer models pre-trained on the source domain to the unlabeled target domain without requiring access to the source data. Most existing SFOD methods leverage pseudo-labels for self-supervised training in the target domain. We investigate the limitations of threshold techniques to obtain high-quality pseudo-labels. In response, we design the Sequential Source-Free domain adaptive Object Detection (S-SFOD) algorithm, which enhances the quality of pseudo-labels at both the image and instance levels. At the image level, we reconstruct the training dataset, prioritizing the training of images that yield more reliable pseudo-labels to help the model acquire valuable target domain knowledge in the initial training stages. At the instance level, we introduce an adaptive local-global threshold method to balance the quality and quantity of pseudo-labels by dynamically adjusting the thresholds based on the model’s learning progress. By improving the quality of pseudo-labels through these complementary techniques at both the image and instance levels, we effectively transfer knowledge from the source domain to the target domain. Extensive experiments on multiple cross-domain object detection datasets demonstrate that our proposed method outperforms current state-of-the-art SFOD algorithms. The code and model will be released.

Zitieren

APA

Dong, Y., Li, C., Xie, Y., & Li, Z. (2025). Revisiting Source-Free Domain Adaptation Object Detection in Thresholds. IEEE Transactions on Multimedia, 27, 6976-6985. https://doi.org/10.1109/tmm.2025.3590905

Vancouver

Dong Y, Li C, Xie Y, Li Z. Revisiting Source-Free Domain Adaptation Object Detection in Thresholds. IEEE Transactions on Multimedia. 2025;27:6976-6985. doi:10.1109/tmm.2025.3590905

BibTeX
@article{Dong2025,
  author = {Dong, Yuchen and Li, Chengeyang and Xie, Yongqiang and Li, Zhongbo},
  title = {Revisiting Source-Free Domain Adaptation Object Detection in Thresholds},
  journal = {IEEE Transactions on Multimedia},
  year = {2025},
  volume = {27},
  pages = {6976--6985},
  doi = {10.1109/tmm.2025.3590905}
}
Kostenlos starten →