EUVIMEDEUVIMED entdecken
Crossref

Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter

Zhiyang Chen, Chen Zhang, Hao Fang, Runmin Cong

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3201-3209

DOI: 10.1609/aaai.v40i5.37314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhiyang Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater Instance Segmentation (UIS), integrating pixel-level understanding and instance-level discrimination, is a pivotal technology in marine resource exploration and ecological protection. In recent years, large-scale pretrained visual foundation models, exemplified by DINO, have advanced rapidly and demonstrated remarkable performance on complex downstream tasks. In this paper, we demonstrate that DINO can serve as an effective feature learner for UIS, and we introduce DiveSeg, a novel framework built upon two insightful components: (1) The AquaStyle Aligner, designed to embed underwater color style features into the DINO fine-tuning process, facilitating better adaptation to the underwater domain. (2) The ObjectPrior Prompter, which incorporates binary segmentation-based prompts to deliver object-level priors, provides essential guidance for instance segmentation task that requires both object- and instance-level reasoning. We conduct thorough experiments on the popular UIIS and USIS10K datasets, and the results show that DiveSeg achieves the state-of-the-art performance.

Zitieren

APA

Chen, Z., Zhang, C., Fang, H., & Cong, R. (2026). Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3201-3209. https://doi.org/10.1609/aaai.v40i5.37314

Vancouver

Chen Z, Zhang C, Fang H, Cong R. Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3201-3209. doi:10.1609/aaai.v40i5.37314

BibTeX
@article{Chen2026,
  author = {Chen, Zhiyang and Zhang, Chen and Fang, Hao and Cong, Runmin},
  title = {Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3201--3209},
  doi = {10.1609/aaai.v40i5.37314}
}
Kostenlos starten →