Melola Discovery

← Melola Discovery

Jurnal SINTA 2

Improving Robustness Using MixUp and CutMix Augmentation for Corn Leaf Diseases Classification based on ConvMixer Architecture

Journal of ICT Research and Applications (JICTRA) · Vol. 17 No. 2 (2023) · pp. 167–180

DOI
10.5614/itbj.ict.res.appl.2023.17.2.3
ISSN
2338-5499, 2337-5787
Published
2023-08-31
Publisher
DRI - ITB
Language
eng

Abstract

Corn leaf diseases such as blight spot, gray leaf spot, and common rust still lurk in corn fields. This problem must be solved to help corn farmers. The ConvMixer model, consisting of a patch embedding layer, is a new model with a simple structure. When training a model with ConvMixer, improvisation is an important part that needs to be further explored to achieve better accuracy. By using advanced data augmentation techniques such as MixUp and CutMix, the robustness of ConvMixer model can be well achieved for corn leaf diseases classification. We describe experimental evidence in this article using precision, recall, accuracy score, and F1 score as performance metrics. As a result, it turned out that the training model with the data set without extension on the ConvMixer model achieved an accuracy of 0.9812, but this could still be improved. In fact, when we used the MixUp and CutMix augmentation, the training model results increased significantly to 0.9925 and 0.9932, respectively.

Keywords

Collaboration network of the authors

5 authors · 7 co-authorship links · 4 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Chaoyang University of Technology
  • Satya Wacana Christian University
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Yos Richard BeehSatya Wacana Christian University1
Pratyaksa Ocsa Nugraha SaianSatya Wacana Christian University1
Agus Cahyo NugrohoChaoyang University of Technology1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journals.itb.ac.id/index.php/jictra/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Improving Robustness Using MixUp and CutMix Augmentation for Corn Leaf Diseases Classification based on ConvMixer Architecture</dc:title>
	<dc:creator>Li , Li Hua</dc:creator>
	<dc:creator>Tanone, Radius</dc:creator>
	<dc:subject xml:lang="en-US">ConvMixer</dc:subject>
	<dc:subject xml:lang="en-US">corn leaf diseases</dc:subject>
	<dc:subject xml:lang="en-US">CutMix</dc:subject>
	<dc:subject xml:lang="en-US">data augmentation</dc:subject>
	<dc:subject xml:lang="en-US">MixUp</dc:subject>
	<dc:subject xml:lang="en-US">robustness</dc:subject>
	<dc:description xml:lang="en-US">Corn leaf diseases such as blight spot, gray leaf spot, and common rust still lurk in corn fields. This problem must be solved to help corn farmers. The ConvMixer model, consisting of a patch embedding layer, is a new model with a simple structure. When training a model with ConvMixer, improvisation is an important part that needs to be further explored to achieve better accuracy. By using advanced data augmentation techniques such as MixUp and CutMix, the robustness of ConvMixer model can be well achieved for corn leaf diseases classification. We describe experimental evidence in this article using precision, recall, accuracy score, and F1 score as performance metrics. As a result, it turned out that the training model with the data set without extension on the ConvMixer model achieved an accuracy of 0.9812, but this could still be improved. In fact, when we used the MixUp and CutMix augmentation, the training model results increased significantly to 0.9925 and 0.9932, respectively.</dc:description>
	<dc:publisher xml:lang="en-US">DRI - ITB</dc:publisher>
	<dc:date>2023-08-31</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journals.itb.ac.id/index.php/jictra/article/view/18894</dc:identifier>
	<dc:identifier>10.5614/itbj.ict.res.appl.2023.17.2.3</dc:identifier>
	<dc:source xml:lang="en-US">Journal of ICT Research and Applications; Vol. 17 No. 2 (2023); 167-180</dc:source>
	<dc:source>2338-5499</dc:source>
	<dc:source>2337-5787</dc:source>
	<dc:source>10.5614/itbj.ict.res.appl.2023.17.2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journals.itb.ac.id/index.php/jictra/article/view/18894/6295</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2023 Journal of ICT Research and Applications</dc:rights>
</oai_dc:dc>