A Comparative Study of Deep Learning Classification Methods on a Small Environmental Microorganism Image Dataset (EMDS-6): From Convolutional Neural Networks to Visual Transformers

Zhao, Peng; Li, Chen; Rahaman, Md Mamunur; Xu, Hao; Yang, Hechen; Sun, Hongzan; Jiang, Tao; Grzegorzek, Marcin

doi:10.3389/fmicb.2022.792166

Cited by 40 publications

(29 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the EMDS-6 is a very small dataset, 37.5% of the dataset was selected as the training set, 25% as the validation set, and 37.5% as the test set. as in [ 33 ]. In the data augmentation experiment, the same five geometric enhancements as in [ 33 ] were adopted to enhance the EMDS-6 dataset, namely rotation by 90°, 180°, and 270°, as well as up-down and left-right mirror transformations.…”

Section: Resultsmentioning

confidence: 99%

“…However, it is known that CNNs are ineffective in capturing long-distance dependencies in EM images [ 30 ]. Due to the better ability of transformers in capturing long-distance dependencies, Zhao P. et al [ 33 ] first proposed the use of ViTs for an EM image classification study on the EMDS-6 dataset, which was a novel approach compared to others presented by that time. The difference with the present work is that in this study a hybrid transformer-CNN architecture is proposed instead of ViTs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A novel hybrid transformer-CNN architecture for environmental microorganism classification

Shao

Chen

2022

PLoS ONE

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A novel hybrid transformer-CNN architecture for environmental microorganism classification

Shao

Chen

2022

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…In addition, there are also many methods for scheduling the learning rate. However, choosing the best CNN model, optimizer and scheduling the learning rate for your dataset is a difficult problem because it is computationally expensive 25 . It will be necessary to search for optimum CNN model selection and best parameter tuning in the future.…”

Section: Discussionmentioning

confidence: 99%

Effective deep learning for oral exfoliative cytology classification

Sukegawa

Tanaka

Nakano

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The use of sharpness aware minimization (SAM) as an optimizer that achieves high performance for convolutional neural networks (CNNs) is attracting attention in various fields of deep learning. We used deep learning to perform classification diagnosis in oral exfoliative cytology and to analyze performance, using SAM as an optimization algorithm to improve classification accuracy. The whole image of the oral exfoliation cytology slide was cut into tiles and labeled by an oral pathologist. CNN was VGG16, and stochastic gradient descent (SGD) and SAM were used as optimizers. Each was analyzed with and without a learning rate scheduler in 300 epochs. The performance metrics used were accuracy, precision, recall, specificity, F1 score, AUC, and statistical and effect size. All optimizers performed better with the rate scheduler. In particular, the SAM effect size had high accuracy (11.2) and AUC (11.0). SAM had the best performance of all models with a learning rate scheduler. (AUC = 0.9328) SAM tended to suppress overfitting compared to SGD. In oral exfoliation cytology classification, CNNs using SAM rate scheduler showed the highest classification performance. These results suggest that SAM can play an important role in primary screening of the oral cytological diagnostic environment.

show abstract

“…In this article, we design the following two experiments to test whether the EMDS-6 dataset can compare the performance of different classifiers (Li et al, 2019 ; Zhao et al, 2022 ). Experiment 1: use traditional machine learning methods to classify images.…”

Section: Methodsmentioning

confidence: 99%

EMDS-6: Environmental Microorganism Image Dataset Sixth Version for Image Denoising, Segmentation, Feature Extraction, Classification, and Detection Method Evaluation

Zhao

Rahaman

et al. 2022

Front. Microbiol.

Self Cite

View full text Add to dashboard Cite

Environmental microorganisms (EMs) are ubiquitous around us and have an important impact on the survival and development of human society. However, the high standards and strict requirements for the preparation of environmental microorganism (EM) data have led to the insufficient of existing related datasets, not to mention the datasets with ground truth (GT) images. This problem seriously affects the progress of related experiments. Therefore, This study develops the Environmental Microorganism Dataset Sixth Version (EMDS-6), which contains 21 types of EMs. Each type of EM contains 40 original and 40 GT images, in total 1680 EM images. In this study, in order to test the effectiveness of EMDS-6. We choose the classic algorithms of image processing methods such as image denoising, image segmentation and object detection. The experimental result shows that EMDS-6 can be used to evaluate the performance of image denoising, image segmentation, image feature extraction, image classification, and object detection methods. EMDS-6 is available at the https://figshare.com/articles/dataset/EMDS6/17125025/1.

show abstract

A Comparative Study of Deep Learning Classification Methods on a Small Environmental Microorganism Image Dataset (EMDS-6): From Convolutional Neural Networks to Visual Transformers

Cited by 40 publications

References 38 publications

A novel hybrid transformer-CNN architecture for environmental microorganism classification

A novel hybrid transformer-CNN architecture for environmental microorganism classification

Effective deep learning for oral exfoliative cytology classification

EMDS-6: Environmental Microorganism Image Dataset Sixth Version for Image Denoising, Segmentation, Feature Extraction, Classification, and Detection Method Evaluation

Contact Info

Product

Resources

About