Convolutional neural networks and vision transformers for Plankton Classification

In this paper, we present a study on plankton classification for automated underwater ecosystems monitoring. The study considers the creation of ensembles combining different Convolutional Neural Network (CNN) models and transformer architectures to understand whether different optimization algorith...

Full description

Saved in:
Bibliographic Details
Main Authors: Loris Nanni, Alessandra Lumini, Leonardo Barcellona, Stefano Ghidoni
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S157495412500281X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233615988195328
author Loris Nanni
Alessandra Lumini
Leonardo Barcellona
Stefano Ghidoni
author_facet Loris Nanni
Alessandra Lumini
Leonardo Barcellona
Stefano Ghidoni
author_sort Loris Nanni
collection DOAJ
description In this paper, we present a study on plankton classification for automated underwater ecosystems monitoring. The study considers the creation of ensembles combining different Convolutional Neural Network (CNN) models and transformer architectures to understand whether different optimization algorithms can result in more robust and efficient classification across various plankton datasets. Tests involved different variants of the Adam optimizer and multiple learning rate variation strategies applied to several CNN architectures, building an ensemble of classifiers. Such ensembles were tested together with transformer-based models in a detailed comparative analysis considering feature extraction efficiency, computational cost, and robustness to species imbalances. The study highlights the performance of individual nets and ensembles on multiple plankton datasets, and discusses the potential for generalizing this approach to broader aquatic ecosystems. Experiments demonstrate that combining diverse neural network models in a heterogeneous ensemble significantly improves performance with respect to other state-of-the-art approaches across all the problems considered. Final results show that the ensemble-based approach achieves a remarkable accuracy improvement over individual CNN models and over standalone Vision Transformers.
format Article
id doaj-art-cba121cc69a942ca8343abf4f5e3ebde
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-cba121cc69a942ca8343abf4f5e3ebde2025-08-20T05:05:28ZengElsevierEcological Informatics1574-95412025-12-019010327210.1016/j.ecoinf.2025.103272Convolutional neural networks and vision transformers for Plankton ClassificationLoris Nanni0Alessandra Lumini1Leonardo Barcellona2Stefano Ghidoni3Department of Information Engineering, University of Padova, Via Giovanni Gradenigo, 6b, Padova, 35131, ItalyDepartment of Computer Science and Engineering, University of Bologna, via dell’Università 50, Cesena, 47522, Italy; Corresponding author.Department of Information Engineering, University of Padova, Via Giovanni Gradenigo, 6b, Padova, 35131, ItalyDepartment of Information Engineering, University of Padova, Via Giovanni Gradenigo, 6b, Padova, 35131, ItalyIn this paper, we present a study on plankton classification for automated underwater ecosystems monitoring. The study considers the creation of ensembles combining different Convolutional Neural Network (CNN) models and transformer architectures to understand whether different optimization algorithms can result in more robust and efficient classification across various plankton datasets. Tests involved different variants of the Adam optimizer and multiple learning rate variation strategies applied to several CNN architectures, building an ensemble of classifiers. Such ensembles were tested together with transformer-based models in a detailed comparative analysis considering feature extraction efficiency, computational cost, and robustness to species imbalances. The study highlights the performance of individual nets and ensembles on multiple plankton datasets, and discusses the potential for generalizing this approach to broader aquatic ecosystems. Experiments demonstrate that combining diverse neural network models in a heterogeneous ensemble significantly improves performance with respect to other state-of-the-art approaches across all the problems considered. Final results show that the ensemble-based approach achieves a remarkable accuracy improvement over individual CNN models and over standalone Vision Transformers.http://www.sciencedirect.com/science/article/pii/S157495412500281XPlanktonNeural networksEnsembleTransformers
spellingShingle Loris Nanni
Alessandra Lumini
Leonardo Barcellona
Stefano Ghidoni
Convolutional neural networks and vision transformers for Plankton Classification
Ecological Informatics
Plankton
Neural networks
Ensemble
Transformers
title Convolutional neural networks and vision transformers for Plankton Classification
title_full Convolutional neural networks and vision transformers for Plankton Classification
title_fullStr Convolutional neural networks and vision transformers for Plankton Classification
title_full_unstemmed Convolutional neural networks and vision transformers for Plankton Classification
title_short Convolutional neural networks and vision transformers for Plankton Classification
title_sort convolutional neural networks and vision transformers for plankton classification
topic Plankton
Neural networks
Ensemble
Transformers
url http://www.sciencedirect.com/science/article/pii/S157495412500281X
work_keys_str_mv AT lorisnanni convolutionalneuralnetworksandvisiontransformersforplanktonclassification
AT alessandralumini convolutionalneuralnetworksandvisiontransformersforplanktonclassification
AT leonardobarcellona convolutionalneuralnetworksandvisiontransformersforplanktonclassification
AT stefanoghidoni convolutionalneuralnetworksandvisiontransformersforplanktonclassification