EUVIMEDEUVIMED entdecken
Crossref

Deep Learning for Marine Animal Recognition: A Comparative Study of CNN Architectures and Triplet Loss Optimization

Mir Ihrar Ali

Current Natural Sciences and Engineering · 28.06.2026 · 3 (1) · 964-976

DOI: 10.63015/3ai-2503.3.1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Current Natural Sciences and Engineering, online erschienen am 28.06.2026. Verfasst von Mir Ihrar Ali.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The conservation of marine biodiversity has become. increasingly critical in the face of climate change and environ- mental degradation. Identifying individual animals is essential for understanding species behavior, migration patterns, and population dynamics, yet traditional methods remain time-intensive and reliant on expert observation. This study leverages deep learning to automate individual whale and dolphin identification using data from the Kaggle Happywhale challenge. The performance of several Convolutional Neural Network (CNN) architectures is evaluated, including ResNet, DenseNet, EfficientNet, and In- ceptionV3, and explore the combination of Softmax classification with a semi-hard triplet-loss approach. The results reveal that InceptionV3 achieves superior accuracy, while the hybrid Softmax and triplet-loss method offers limited benefits, hindered by dataset challenges such as the prevalence of hard triplets. These findings emphasize the need for refined loss strategies to handle unbalanced datasets in wildlife identification. This work highlights the potential of machine learning to revolutionize marine conservation efforts by enabling scalable and efficient individual recognition systems.

Zitieren

APA

Ali, M. I. (2026). Deep Learning for Marine Animal Recognition: A Comparative Study of CNN Architectures and Triplet Loss Optimization. Current Natural Sciences and Engineering, 3(1), 964-976. https://doi.org/10.63015/3ai-2503.3.1

Vancouver

Ali MI. Deep Learning for Marine Animal Recognition: A Comparative Study of CNN Architectures and Triplet Loss Optimization. Current Natural Sciences and Engineering. 2026;3(1):964-976. doi:10.63015/3ai-2503.3.1

BibTeX
@article{Ali2026,
  author = {Ali, Mir Ihrar},
  title = {Deep Learning for Marine Animal Recognition: A Comparative Study of CNN Architectures and Triplet Loss Optimization},
  journal = {Current Natural Sciences and Engineering},
  year = {2026},
  volume = {3},
  number = {1},
  pages = {964--976},
  doi = {10.63015/3ai-2503.3.1}
}
Kostenlos starten →