Izvorni znanstveni članak

https://doi.org/10.31217/p.38.2.6

Zero-Shot Learning in Maritime Domain: Classification of Marine Objects using CLIP

Ivan Lorencin ; Sveučilište Jurja Dobrile u Puli, Pula, Hrvatska
Domagoj Frank orcid.org/0000-0002-7907-7961 ; Sveučilište Sjever, Koprivnica, Hrvatska
Damir Vusić orcid.org/0000-0001-9972-2246 ; Sveučilište Sjever, Koprivnica, Hrvatska

Sažetak

Maritime security and monitoring are essential for global trade, environmental protection,and national defense. Traditional machine learning models have been effective in recognizing andclassifying maritime objects, but their reliance on large, labeled datasets poses challenges,particularly in dynamic environments where new and unforeseen objects frequently emerge. Thisstudy explores the application of Zero-Shot Learning (ZSL) to the maritime domain, leveraging theCLIP model to classify maritime objects with minimal labeled data. A custom dataset comprising1,438 images was used to evaluate the performance of various CLIP model variants. Our findingsindicate that CLIP models, particularly the "clip-vit-large-patch14-336" variant, achieve highclassification accuracy, with AUC values approaching 1.0 across most classes. However, challengesremain in handling rare or ambiguous classes such as cargo ships, where F2 scores suggestvariability in recall and precision. Additionally, the study highlights the potential limitations ofthese models, including their dependency on dataset diversity and the risk of overfitting to specificdata characteristics. The "clip-vit-large-patch14-336" model is identified as the most balanced andreliable option, offering a strong foundation for enhancing maritime situational awareness andsupporting diverse maritime applications.

Ključne riječi

Clip,Marine Objects,Vision-language models,Transformers,Zero-shoot learning

Hrčak ID:

324330

URI

https://hrcak.srce.hr/324330

Datum izdavanja:

20.12.2024.

Posjeta: 0 *