Litcius/Paper detail

Multi-species Seagrass Detection Using Semi-supervised Learning

Md Kislu Noman, Syed Mohammed Shamsul Islam, Jumana Abu-Khalaf, Paul S. Lavery

202119 citationsDOIOpen Access PDF

Abstract

This paper introduces a semi-supervised two-stage framework that leverages a large collection of unlabelled seagrass data with the guidance of a small amount of labelled seagrass data. First, a state-of-the-art Convolutional Neural Network (CNN) named EfficientNet is trained on a small number of labelled seagrass image patches. Next, the trained classifier generates pseudo labels for the unlabelled seagrass image patches. Finally, this classifier is retrained on the combination of labelled and pseudo labelled seagrass image patches. This approach achieves 98.0% multi-species detection accuracy on a newly developed seagrass dataset. Our approach on the publicly available ‘DeepSeagrass’ dataset achieves an overall accuracy of 91.3% and 93.0%, which outperforms the state-of-the-art multi-species seagrass detection accuracy of 88.2% and 92.4% for four and five classes, respectively.

Topics & Concepts

SeagrassClassifier (UML)Convolutional neural networkComputer scienceArtificial intelligencePattern recognition (psychology)EcologyEcosystemBiologyIdentification and Quantification in FoodCoral and Marine Ecosystems StudiesIchthyology and Marine Biology