EUVIMEDEUVIMED entdecken
Crossref

Unsupervised Maritime Vessel Re-Identification With Multi-Level Contrastive Learning

Qian Zhang, Mingxin Zhang, Jinghe Liu, Xuanyu He, Ran Song, Wei Zhang

IEEE Transactions on Intelligent Transportation Systems · 2023-05 · 24 (5) · 5406-5418

DOI: 10.1109/tits.2023.3243591 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-05. Verfasst von Qian Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Plan of China, Natural Science Foundation of Shandong Province for Distinguished Young Scholars.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Re-identification (re-ID) of maritime vessels plays an important role in marine surveillance, but remains highly unexplored due to the lack of large-scale annotated datasets. In vessel re-ID, contrastive methods are supposed to learn discriminative representation from unlabeled vessel images in an unsupervised manner. However, directly introducing classical instance-level contrastive methods to maritime vessel re-ID suffers from the difficulty of finding vessel images with the same pseudo label as positive images, which potentially leads to inefficient training and unsatisfactory performance. This paper proposes a simple but effective method to solve such a hard positive problem. Our method takes all images in an intra-batch cluster as positives and excludes them from the set of negative samples when computing instance-level contrastive loss. Based on this strategy, we construct a multi-level contrastive learning (MCL) framework for vessel re-ID trained with the specifically designed intra-batch cluster-level contrastive loss along with the instance-level one. Experiments on a newly proposed dataset consisting of 1,248 vessel identities show that MCL achieves the state-of-the-art performance compared with other unsupervised methods.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Plan of China
  • Natural Science Foundation of Shandong Province for Distinguished Young Scholars
  • Project for Self-Developed Innovation Team of Jinan City

Zitieren

APA

Zhang, Q., Zhang, M., Liu, J., He, X., Song, R., & Zhang, W. (2023). Unsupervised Maritime Vessel Re-Identification With Multi-Level Contrastive Learning. IEEE Transactions on Intelligent Transportation Systems, 24(5), 5406-5418. https://doi.org/10.1109/tits.2023.3243591

Vancouver

Zhang Q, Zhang M, Liu J, He X, Song R, Zhang W. Unsupervised Maritime Vessel Re-Identification With Multi-Level Contrastive Learning. IEEE Transactions on Intelligent Transportation Systems. 2023;24(5):5406-5418. doi:10.1109/tits.2023.3243591

BibTeX
@article{Zhang2023,
  author = {Zhang, Qian and Zhang, Mingxin and Liu, Jinghe and He, Xuanyu and Song, Ran and Zhang, Wei},
  title = {Unsupervised Maritime Vessel Re-Identification With Multi-Level Contrastive Learning},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  volume = {24},
  number = {5},
  pages = {5406--5418},
  doi = {10.1109/tits.2023.3243591}
}
Kostenlos starten →