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


  • Li Hua Li Department of Information Management, Chaoyang University of Technology, No. 168?, Jifeng E Rd, Wufeng District, Taichung City, 413, Taiwan
  • Radius Tanone Department of Information Management, Chaoyang University of Technology, No. 168?, Jifeng E Rd, Wufeng District, Taichung City, 413, Taiwan



ConvMixer, corn leaf diseases, CutMix, data augmentation, MixUp, robustness


Corn leaf diseases such as blight spot, gray leaf spot, and common rust still lurk in corn fields. Thisproblemmustbe 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 modelwithConvMixer, improvisation is an important part that needs to befurther explored to achieve better accuracy. By using advanced data augmentation techniques such as MixUp and CutMix, the robustness ofConvMixermodel can be well achievedfor corn leaf diseasesclassification. We describe experimental evidence in thisarticle usingprecision, recall, accuracy score, and F1score as performance metrics. As a result,it turned out thatthe training model with thedata 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 CutMixaugmentation, the training model resultsincreasedsignificantlyto 0.9925 and 0.9932,respectively.


Download data is not yet available.


Lynch, J., Cain, M., Frame, D. & Pierrehumbert, R., Agriculture?s Contribution to Climate Change and Role in Mitigation Is Distinct from Predominantly Fossil CO2-Emitting Sectors, Front. Sustain. Food Syst., 4, 518039, 2021. DOI: 10.3389/FSUFS.2020.518039/BIBTEX.

Timmer, C.P., The Corn Economy of Indonesia, 302p., Cornell University Press, 1987.

Sumarwati, S., Traditional Ecological Knowledge on the Slope of Mount Lawu, Indonesia: All About Non-Rice Food Security, J. Ethn. Foods, 9(1), pp. 1-13, 2022. DOI: 10.1186/S42779-022-00120-Z.

Susanawati., Wijaya, O. & Rizqi, M.B., Local Food Development Strategy in Hilly Areas of Gunungkidul Indonesia, IOP Conf. Ser. Earth Environ. Sci., 1016(1), 012026, 2022. DOI: 10.1088/1755-1315/1016/1/012026.

Waluyati, L.R., Fadhliani, Z., Anjani, H.D., Siregar, A.P., Susilo, K.R. & Setyowati, L., Feasibility Study of a Tropical Sweet Corn Farming at the Center of Innovation and Agrotechnology Universitas Gadjah Mada, IOP Conf. Ser. Earth Environ. Sci., 1005(1), 012030, 2022. DOI: 10.1088/1755-1315/1005/1/012030.

Naylor, R., Falcon, W., Wada, N. & Rochberg, D., Using El Ni-Southern Oscillation Climate Data to Improve Food Policy Planning in Indonesia,? Bulletin of Indonesian Economic Studies, 38(1), pp. 75-91, 2002. DOI: 10.1080/000749102753620293.

Ruminta, R. & Handoko, H., Vurnerability Assessment of Climate Change on Agriculture Sector in the South Sumatra Province, Indonesia, Asian J. Crop Sci., 8(2), pp. 31-42, 2016. DOI: 10.3923/AJCS.2016.31.42.

Xia, X., Wang, Y., Zhou, S., Liu, W. & Wu, H., Genome Sequence Resource for Bipolaris Zeicola, the Cause of Northern Corn Leaf Spot Disease, Phytopathology, 112(5), pp. 1192-1195, 2022. DOI: 10.1094/PHYTO-05-21-0196-A.

Kistner, M.B., Nazar, L., Montenegro, L.D., Cervigni, G.D.L., Galdeano, E. & Iglesias, J., Detecting Sources of Resistance to Multiple Diseases in Argentine Maize (Zea Mays L.) Germplasm, Euphytica, 218(5), 48, 2022. DOI: 10.1007/S10681-022-03000-4.

De Rossi, R.L., Crop Damage, Economic Losses, and the Economic Damage Threshold for Northern Corn Leaf Blight, Crop Protection, 154, pp. 1-10, 2022. DOI: 10.1016/J.CROPRO.2021.105901.

CALS, Diseases of Corn., (Jan. 13, 2022).

Kalidindi, A., Kompalli, P.L., Bandi, S. & Anugu, S.R.R., CT Image Classification of Human Brain using Deep Learning, Int. J. Online Biomed. Eng., 17(1), pp. 51?62, 2021. DOI: 10.3991/IJOE.V17I01.18565.

Lakshmi, K.P., Mekala, K.R., Modala, V. Sai, R. Sree., Devalla, V. & Kompalli, A.B., Leaf Disease Detection and Remedy Recommendation Using CNN Algorithm, Int. J. Online Biomed. Eng., 18(7), pp. 85-100, 2022. DOI: 10.3991/IJOE.V18I07.30383.

Al-Rami, B., Alheeti, K.M.A., Aldosari, W.M., Alshahrani, S.M. & Al-Abrez, S.M., A New Classification Method for Drone-Based Crops in Smart Farming, Int. J. Interact. Mob. Technol., 16(9), pp. 164-174, 2022. DOI: 10.3991/IJIM.V16I09.30037.

Basit, A., Siddique, M.A., Bhatti, M.K. & Sarfraz, M.S., Comparison of CNNs and Vision Transformers-Based Hybrid Models Using Gradient Profile Loss for Classification of Oil Spills in SAR Images, Remote Sensing, 14(9), 2085, 2022. DOI: 10.3390/RS14092085.

Guo, M.H., Attention Mechanisms in Computer Vision: A Survey, Computational Visual Media, pp. 331-368, 2022. DOI: 10.1007/S41095-022-0271-Y.

Noola, D.A. & Basavaraju, D.R., Corn Leaf Image Classification Based on Machine Learning Techniques for Accurate Leaf Disease Detection, Int. J. Electr. Comput. Eng., 12(3), pp. 2509-2516, 2022. DOI: 10.11591/IJECE.V12I3.PP2509-2516.

Amin, H., Darwish, A., Hassanien, A.E. & Soliman, M., End-to-End Deep Learning Model for Corn Leaf Disease Classification, IEEE Access, pp. 31103?31115, 2022. DOI: 10.1109/ACCESS.2022.3159678.

Tolstikhin, I.O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J. & Lucic, M., 2021. MLP-Mixer: An All-MLP Architecture for Vision. Advances in Neural Information Processing Systems, 34, pp. 24261-24272, 2021.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. & Uszkoreit, J., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, pp. 1-22, 2020. DOI:2010.11929.

Trockman, A. & Kolter, J.Z., Patches Are All You Need?, pp.1-16 ,2022. DOI:2201.09792.

Zhang, H., Cisse, M., Dauphin, Y.N. & Lopez-Paz, D., Mixup: Beyond Empirical Risk Minimization, pp. 1-13, 2017. DOI:1710.09412.

Yun, S., Han, D., Oh, S. J., Chun, S., Choe, J. & Yoo, Y., CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features, EEE/CVF International Conference on Computer Vision (ICCV), pp. 6022-6031, 2019. DOI: 10.1109/ICCV.2019.00612.

Zhang, Z., Bengali Handwritten Grapheme Recognition Using CutMix-Based Data Augmentation, ACM Int. Conf. Proceeding Ser., pp. 145-149, 2021. DOI: 10.1145/3488838.3488863.

Guo, W., Wang, Y. & Han, F., Attention-Guided CutMix Data Augmentation Network for Fine-Grained Bird Recognition, ACM Int. Conf. Proceeding Ser., pp. 1-5, 2021. DOI: 10.1145/3469213.3470323.

Simard, P.Y., LeCun, Y.A., Denker, J.S. & Victorri, B., Transformation Invariance in Pattern Recognition ? Tangent Distance and Tangent Propagation BT - Neural Networks: Tricks of the Trade, Orr, G.B. & Mler, K.-R. Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 239-274, 1998.

Chapelle, O., Weston, J., Bottou, L. & Vapnik, V., Vicinal Risk Minimization, Neural Information Processing Systems, pp. 1-7, 2000.

Keras, Mixup Augmentation for Image Classification. (Apr. 14, 2022).

Van Rijsbergen, C.J., Information Retrieval, 2nd ed. USA: Butterworth-Heinemann, 1979.

Sasaki, Y., The Truth of the F-Measure, Teach Tutor Material, 2007.

Kaggle, Bangladeshi Crops Disease Dataset. (Mar. 29, 2022).

DeVries, T. & Taylor, G.W., Improved Regularization of Convolutional Neural Networks with Cutout, pp. 1-8, 2017. DOI: 10.48550/arxiv.1708.04552.

Li, L.H., & Tanone, R., MLP-Mixer Approach for Corn Leaf Diseases Classification, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 13758 LNAI, pp. 204-215, 2022. DOI: 10.1007/978-3-031-21967-2_17.




How to Cite

Li , L. H., & Tanone, R. (2023). Improving Robustness Using MixUp and CutMix Augmentation for Corn Leaf Diseases Classification based on ConvMixer Architecture. Journal of ICT Research and Applications, 17(2), 167-180.