Document of bibliographic reference 405271

BibliographicReference record

Type
Bibliographic resource
Type of document
Journal article
BibLvlCode
AS
Title
FishAI: Automated hierarchical marine fish image classification with vision transformer
Abstract
To address the issues of high demand for efficiently recognizing fish species in marine scientific research, such as impact assessments on biodiversity and monitoring, an automated hierarchical image classification web-based platform, named FishAI, was developed. Trained with marine fish images collected from the World Register of Marine Species, FishAI used the Vision Transformer (ViT) model, to classify fish. The model considers hierarchy levels, covering 3 classes, 38 orders, 154 families, 438 genera, and 808 species. The FishAI achieved accuracies of 0.975 (Class), 0.798 (Order), 0.743 (Family), 0.638 (Genus), and 0.626 (Species) on test images, respectively, by using the hyperparameter optimization. Comparison between ViT and other baseline backbones proves its superiority by capturing long-distance dependency. In addition, FishAI yields the top-5 prediction accuracies of 1.000 (Class), 0.887 (Order), 0.816 (Family), 0.729 (Genus), and 0.727 (Species), respectively. In order to further enhance the practicality of FishAI, the user-friendly graphic interface (http://www.csbio.sjtu.edu.cn/bioinf/FishAI/) facilitates its easy-to-use application. Furthermore, interpretability analysis by Grad-CAM provides a visual explanation of the highlighted regions on the images for FishAI's prediction among different hierarchies.
Bibliographic citation
Yang, C.; Zhou, P.; Wang, C.-S.; Fu, G.-Y.; Xu, X.-W.; Niu, Z.; Zhu, L.; Yuan, Y.; Shen, H.-B.; Pan, X. (2024). FishAI: Automated hierarchical marine fish image classification with vision transformer. Eng. Rep. 6(12): e12992. https://dx.doi.org/10.1002/eng2.12992
Topic
Marine
Is peer reviewed
true
Access rights
open access
Is accessible for free
true

Authors

author
Name
Chenghan Yang
author
Name
Peng Zhou
author
Name
Chun-Sheng Wang
author
Name
Ge-Yi Fu
author
Name
Xue-Wei Xu
author
Name
Zhibin Niu
author
Name
Lin Zhu
author
Name
Ye Yuan
author
Name
Hong-Bin Shen
author
Name
Xiaoyong Pan

Links

referenced creativework
type
DOI
accessURL
https://dx.doi.org/10.1002/eng2.12992

taxonomic terms

taxonomic terms associated with this publication
Pisces [Fish]

Document metadata

date created
2025-01-13
date modified
2025-01-13