EUVIMEDEUVIMED entdecken
Crossref

HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation

Pingping Zhang, Tianyu Yan, Yuhao Wang, Yang Liu, Tongdan Tang, Yili Ma, Long Lv, Feng Tian, Weibing Sun, Huchuan Lu

IEEE Transactions on Image Processing · 2026 · 35 · 3311-3323

DOI: 10.1109/tip.2026.3674678 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Pingping Zhang und 9 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Aquatic Organisms, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 84 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Open Fund of the Key Laboratory of Data Science and Smart Education, Dalian Science and Technology Innovation Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Marine Animal Segmentation (MAS) aims at identifying and segmenting marine animals from complex marine environments. Most of previous deep learning-based MAS methods struggle with the long-distance modeling issue. Recently, Segment Anything Model (SAM) has gained popularity in general image segmentation. However, it lacks of perceiving fine-grained details and frequency information. To this end, we propose a novel learning framework, named Hierarchical Frequency Prompted SAM (HFP-SAM) for high-performance MAS. First, we design a Frequency Guided Adapter (FGA) to efficiently inject marine scene information into the frozen SAM backbone through frequency domain prior masks. Additionally, we introduce a Frequency-aware Point Selection (FPS) to generate highlighted regions through frequency analysis. These regions are combined with the coarse predictions of SAM to generate point prompts and integrate into SAM's decoder for fine predictions. Finally, to obtain comprehensive segmentation masks, we introduce a Full-View Mamba (FVM) to efficiently extract spatial and channel contextual information with linear computational complexity. Extensive experiments on four public datasets demonstrate the superior performance of our approach. We will make our code publicly available upon the acceptance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedAquatic OrganismsDeep LearningAnimalsAlgorithmsDatabases, Factual

Förderung

  • National Natural Science Foundation of China
  • Open Fund of the Key Laboratory of Data Science and Smart Education
  • Dalian Science and Technology Innovation Fund
  • Fundamental Research Funds for the Central Universities
  • Natural Science Foundation of Liaoning Province

Zitieren

APA

Zhang, P., Yan, T., Wang, Y., Liu, Y., Tang, T., Ma, Y., Lv, L., Tian, F., Sun, W., & Lu, H. (2026). HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation. IEEE Transactions on Image Processing, 35, 3311-3323. https://doi.org/10.1109/tip.2026.3674678

Vancouver

Zhang P, Yan T, Wang Y, Liu Y, Tang T, Ma Y, et al. HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation. IEEE Transactions on Image Processing. 2026;35:3311-3323. doi:10.1109/tip.2026.3674678

BibTeX
@article{Zhang2026,
  author = {Zhang, Pingping and Yan, Tianyu and Wang, Yuhao and Liu, Yang and Tang, Tongdan and Ma, Yili and Lv, Long and Tian, Feng and Sun, Weibing and Lu, Huchuan},
  title = {HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {3311--3323},
  doi = {10.1109/tip.2026.3674678}
}
Kostenlos starten →