Cargando…

A novel hybrid transformer-CNN architecture for environmental microorganism classification

The success of vision transformers (ViTs) has given rise to their application in classification tasks of small environmental microorganism (EM) datasets. However, due to the lack of multi-scale feature maps and local feature extraction capabilities, the pure transformer architecture cannot achieve g...

Descripción completa

Detalles Bibliográficos
Autores principales: Shao, Ran, Bi, Xiao-Jun, Chen, Zheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9651547/
https://www.ncbi.nlm.nih.gov/pubmed/36367879
http://dx.doi.org/10.1371/journal.pone.0277557
_version_ 1784828257288323072
author Shao, Ran
Bi, Xiao-Jun
Chen, Zheng
author_facet Shao, Ran
Bi, Xiao-Jun
Chen, Zheng
author_sort Shao, Ran
collection PubMed
description The success of vision transformers (ViTs) has given rise to their application in classification tasks of small environmental microorganism (EM) datasets. However, due to the lack of multi-scale feature maps and local feature extraction capabilities, the pure transformer architecture cannot achieve good results on small EM datasets. In this work, a novel hybrid model is proposed by combining the transformer with a convolution neural network (CNN). Compared to traditional ViTs and CNNs, the proposed model achieves state-of-the-art performance when trained on small EM datasets. This is accomplished in two ways. 1) Instead of the original fixed-size feature maps of the transformer-based designs, a hierarchical structure is adopted to obtain multi-scale feature maps. 2) Two new blocks are introduced to the transformer’s two core sections, namely the convolutional parameter sharing multi-head attention block and the local feed-forward network block. The ways allow the model to extract more local features compared to traditional transformers. In particular, for classification on the sixth version of the EM dataset (EMDS-6), the proposed model outperforms the baseline Xception by 6.7 percentage points, while being 60 times smaller in parameter size. In addition, the proposed model also generalizes well on the WHOI dataset (accuracy of 99%) and constitutes a fresh approach to the use of transformers for visual classification tasks based on small EM datasets.
format Online
Article
Text
id pubmed-9651547
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-96515472022-11-15 A novel hybrid transformer-CNN architecture for environmental microorganism classification Shao, Ran Bi, Xiao-Jun Chen, Zheng PLoS One Research Article The success of vision transformers (ViTs) has given rise to their application in classification tasks of small environmental microorganism (EM) datasets. However, due to the lack of multi-scale feature maps and local feature extraction capabilities, the pure transformer architecture cannot achieve good results on small EM datasets. In this work, a novel hybrid model is proposed by combining the transformer with a convolution neural network (CNN). Compared to traditional ViTs and CNNs, the proposed model achieves state-of-the-art performance when trained on small EM datasets. This is accomplished in two ways. 1) Instead of the original fixed-size feature maps of the transformer-based designs, a hierarchical structure is adopted to obtain multi-scale feature maps. 2) Two new blocks are introduced to the transformer’s two core sections, namely the convolutional parameter sharing multi-head attention block and the local feed-forward network block. The ways allow the model to extract more local features compared to traditional transformers. In particular, for classification on the sixth version of the EM dataset (EMDS-6), the proposed model outperforms the baseline Xception by 6.7 percentage points, while being 60 times smaller in parameter size. In addition, the proposed model also generalizes well on the WHOI dataset (accuracy of 99%) and constitutes a fresh approach to the use of transformers for visual classification tasks based on small EM datasets. Public Library of Science 2022-11-11 /pmc/articles/PMC9651547/ /pubmed/36367879 http://dx.doi.org/10.1371/journal.pone.0277557 Text en © 2022 Shao et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Shao, Ran
Bi, Xiao-Jun
Chen, Zheng
A novel hybrid transformer-CNN architecture for environmental microorganism classification
title A novel hybrid transformer-CNN architecture for environmental microorganism classification
title_full A novel hybrid transformer-CNN architecture for environmental microorganism classification
title_fullStr A novel hybrid transformer-CNN architecture for environmental microorganism classification
title_full_unstemmed A novel hybrid transformer-CNN architecture for environmental microorganism classification
title_short A novel hybrid transformer-CNN architecture for environmental microorganism classification
title_sort novel hybrid transformer-cnn architecture for environmental microorganism classification
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9651547/
https://www.ncbi.nlm.nih.gov/pubmed/36367879
http://dx.doi.org/10.1371/journal.pone.0277557
work_keys_str_mv AT shaoran anovelhybridtransformercnnarchitectureforenvironmentalmicroorganismclassification
AT bixiaojun anovelhybridtransformercnnarchitectureforenvironmentalmicroorganismclassification
AT chenzheng anovelhybridtransformercnnarchitectureforenvironmentalmicroorganismclassification
AT shaoran novelhybridtransformercnnarchitectureforenvironmentalmicroorganismclassification
AT bixiaojun novelhybridtransformercnnarchitectureforenvironmentalmicroorganismclassification
AT chenzheng novelhybridtransformercnnarchitectureforenvironmentalmicroorganismclassification