EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples

Jiamin Lu, Song Zhang, Shili Zhao, Daoliang Li iD, Ran Zhao

Animals · 28.02.2024 · 14 (5) · 755

DOI: 10.3390/ani14050755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 28.02.2024. Verfasst von Jiamin Lu und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Innovation Center for Digital Fishery, China Agricultural University, Beijing 100083, China. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Plan of the Ministry of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fish species identification plays a vital role in marine fisheries resource exploration, yet datasets related to marine fish resources are scarce. In open-water environments, various fish species often exhibit similar appearances and sizes. To solve these issues, we propose a few-shot learning approach to identifying fish species. Our approach involves two key components. Firstly, the embedding module was designed to address the challenges posed by a large number of fish species with similar phenotypes by utilizing the distribution relationships of species in the embedding space. Secondly, a metric function was introduced, effectively enhancing the performance of fish species classification and successfully addressing the issue of limited sample quantity. The proposed model is trained end to end on fish species public datasets including the Croatian fish dataset, Fish4Knowledge and WildFish. Compared with the prototypical networks, our method performs more effectively and improves accuracy by 2% to 10%; it is able to identify fish effectively in small samples sizes and complex scene scenarios. This method provides a valuable technological tool for the development of fisheries resources and the preservation of fish biodiversity.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismfew-shot classificationfish recognitionprototypical networks

Autor:innen und Institutionen

  • National Innovation Center for Digital Fishery, China Agricultural University, Beijing 100083, China.
  • Key Laboratory of Smart Farming Technologies for Aquatic Animal and Livestock, Ministry of Agriculture and Rural Affair, Beijing 100083, China.
  • Beijing Engineering and Technology Research Centre for Internet of Things in Agriculture, China Agriculture University, Beijing 100083, China.
  • College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China.

ORCID-Profile: Daoliang Li

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Plan of the Ministry of Science and Technology

Zitieren

APA

Lu, J., Zhang, S., Zhao, S., Li, D., & Zhao, R. (2024). A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples. Animals, 14(5), 755. https://doi.org/10.3390/ani14050755

Vancouver

Lu J, Zhang S, Zhao S, Li D, Zhao R. A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples. Animals. 2024;14(5):755. doi:10.3390/ani14050755

BibTeX
@article{Lu2024,
  author = {Lu, Jiamin and Zhang, Song and Zhao, Shili and Li, Daoliang and Zhao, Ran},
  title = {A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples},
  journal = {Animals},
  year = {2024},
  volume = {14},
  number = {5},
  pages = {755},
  doi = {10.3390/ani14050755}
}
Kostenlos starten →