EUVIMEDEUVIMED entdecken
Crossref

Boosting Weakly Supervised Object Localization and Segmentation With Domain Adaption

Lei Zhu, Qi She, Qian Chen, Qiushi Ren, Yanye Lu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 8680-8695

DOI: 10.1109/tpami.2024.3411036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Lei Zhu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 95 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised object localization (WSOL), adopting only image-level annotations to learn the pixel-level localization model, can release human resources in the annotation process. Most one-stage WSOL methods learn the localization model with multi-instance learning, making them only activate discriminative object parts rather than the whole object. In our work, we attribute this problem to the domain shift between the training and test process of WSOL and provide a novel perspective that views WSOL as a domain adaption (DA) task. Under this perspective, a DA-WSOL pipeline is elaborated to better assist WSOL with DA approaches by considering the specificities for the adaption of WSOL. Our DA-WSOL pipeline can discern the source-related and the Universum samples from other target samples based on a proposed target sampling strategy and then utilize them to solve the sample unbalancing and label unmatching between the source and target domain of WSOL. Experiments show that our pipeline outperforms SOTA methods on three WSOL benchmarks and can improve the performance of downstream weakly supervised semantic segmentation tasks.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Shenzhen Science and Technology Program
  • High-grade
  • Precision and Advanced University Discipline Construction Project of Beijing

Zitieren

APA

Zhu, L., She, Q., Chen, Q., Ren, Q., & Lu, Y. (2024). Boosting Weakly Supervised Object Localization and Segmentation With Domain Adaption. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 8680-8695. https://doi.org/10.1109/tpami.2024.3411036

Vancouver

Zhu L, She Q, Chen Q, Ren Q, Lu Y. Boosting Weakly Supervised Object Localization and Segmentation With Domain Adaption. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):8680-8695. doi:10.1109/tpami.2024.3411036

BibTeX
@article{Zhu2024,
  author = {Zhu, Lei and She, Qi and Chen, Qian and Ren, Qiushi and Lu, Yanye},
  title = {Boosting Weakly Supervised Object Localization and Segmentation With Domain Adaption},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {8680--8695},
  doi = {10.1109/tpami.2024.3411036}
}
Kostenlos starten →