{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T20:26:36Z","timestamp":1793737596813,"version":"4.6.1"},"reference-count":47,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Academic Exchange Service (DAAD) Germany","award":["91788784"],"award-info":[{"award-number":["91788784"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Plants"],"abstract":"<jats:p>Reliable identification of maize leaf diseases is critical for mitigating crop losses, particularly in regions where farmers have limited access to experts. Although vision transformers (ViTs) have recently demonstrated strong performance in image recognition, their weak inductive bias and limited modeling of local texture patterns make them non-ideal for fine-grained maize leaf disease classification. To address these limitations, we propose ConvDeiT-Tiny, a lightweight hybrid ViT that improves DeiT-Ti by placing depthwise convolutions in parallel with multi-head self-attention modules in the first three transformer blocks. The local and global features captured by the convolution and attention modules are concatenated along the embedding dimension and fused using a multilayer perceptron. This results in richer token representations without significantly increasing model size. Across three datasets, ConvDeiT-Tiny (6.9 M parameters) consistently outperformed DeiT-Ti, DeiT-Ti-Distilled, and DeiT-S (21.7 M parameters) when trained from scratch. With transfer learning, ConvDeiT-Tiny achieved an accuracy of 99.15%, 99.35%, and 98.60% on the CD&amp;S, primary, and Kaggle datasets, respectively, surpassing many previous studies with far fewer parameters. For explainability, we present gradient-weighted transformer attribution visualizations showing the disease lesions driving model predictions. These results indicate that injecting local inductive bias in early transformer blocks is beneficial for accurate maize leaf disease classification.<\/jats:p>","DOI":"10.3390\/plants15060982","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T13:53:34Z","timestamp":1774274014000},"page":"982","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ConvDeiT-Tiny: Adding Local Inductive Bias to DeiT-Ti for Enhanced Maize Leaf Disease Classification"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7413-6815","authenticated-orcid":false,"given":"Damaris","family":"Waema","sequence":"first","affiliation":[{"name":"Department of Computing, Jomo Kenyatta University of Agriculture and Technology, Nairobi P.O. BOX 62000-00200, Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6352-5525","authenticated-orcid":false,"given":"Waweru","family":"Mwangi","sequence":"additional","affiliation":[{"name":"Department of Computing, Jomo Kenyatta University of Agriculture and Technology, Nairobi P.O. BOX 62000-00200, Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0857-2452","authenticated-orcid":false,"given":"Petronilla","family":"Muriithi","sequence":"additional","affiliation":[{"name":"Department of Computing, Jomo Kenyatta University of Agriculture and Technology, Nairobi P.O. BOX 62000-00200, Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1007\/978-981-99-7711-6_41","article-title":"Maize Leaf Disease Detection Using Vision Transformers (ViTs) and CNN-Based Classifiers: Comparative Analysis","volume":"Volume 376","author":"Bhattacharyya","year":"2024","journal-title":"Human-Centric Smart Computing"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhou, H., Su, Y., Chen, J., Li, J., Ma, L., Liu, X., Lu, S., and Wu, Q. (2024). Maize Leaf Disease Recognition Based on Improved Convolutional Neural Network ShuffleNetV2. Plants, 13.","DOI":"10.3390\/plants13121621"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"31103","DOI":"10.1109\/ACCESS.2022.3159678","article-title":"End-to-End Deep Learning Model for Corn Leaf Disease Classification","volume":"10","author":"Amin","year":"2022","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2479","DOI":"10.1007\/s00521-024-10769-z","article-title":"Utilizing Convolutional Neural Networks and Vision Transformers for Precise Corn Leaf Disease Identification","volume":"37","author":"Pacal","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"28096","DOI":"10.1109\/ACCESS.2024.3367443","article-title":"A Lightweight Meta-Ensemble Approach for Plant Disease Detection Suitable for IoT-Based Environments","volume":"12","author":"Maurya","year":"2024","journal-title":"IEEE Access"},{"key":"ref_6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_7","unstructured":"Wadekar, S.N., and Chaurasia, A. (2022). MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., and Zhang, L. (2021, January 10\u201317). CvT: Introducing Convolutions to Vision Transformers. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref_9","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., and Sagun, L. (2021, January 8\u201324). ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases. Proceedings of the 38th International Conference on Machine Learning, Virtual. Available online: http:\/\/proceedings.mlr.press\/v139\/d-ascoli21a\/d-ascoli21a.pdf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s44163-025-00340-7","article-title":"Enhancing Sugarcane Leaf Disease Classification Using Vision Transformers over CNNs","volume":"5","author":"Miryala","year":"2025","journal-title":"Discov. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in Vision: A Survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e70513","DOI":"10.1002\/fsn3.70513","article-title":"Enhanced Maize Leaf Disease Detection and Classification Using an Integrated CNN-ViT Model","volume":"13","author":"Shandilya","year":"2025","journal-title":"Food Sci. Nutr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102245","DOI":"10.1016\/j.ecoinf.2023.102245","article-title":"Vision Transformer Meets Convolutional Neural Network for Plant DiseaseClassification","volume":"77","author":"Thakur","year":"2023","journal-title":"Ecol. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"15549","DOI":"10.1007\/s00500-023-09071-2","article-title":"DCTN: A Dense Parallel Network Combining CNN and Transformer for Identifying Plant Disease in Field","volume":"27","author":"Pang","year":"2023","journal-title":"Soft Comput."},{"key":"ref_15","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., and J\u00e9gou, H. (2021, January 8\u201324). Training Data-Efficient Image Transformers & Distillation through Attention. Proceedings of the 38th International Conference on Machine Learning, Virtual. Available online: http:\/\/proceedings.mlr.press\/v139\/touvron21a\/touvron21a.pdf."},{"key":"ref_16","unstructured":"Hendrycks, D., and Gimpel, K. (2016). Gaussian Error Linear Units (GELUs). arXiv."},{"key":"ref_17","first-page":"e12864","article-title":"GMM-LIME Explainable Machine Learning Model for Interpreting Sensor-Based Human Gait","volume":"6","author":"Mulwa","year":"2024","journal-title":"Eng. Rep."},{"key":"ref_18","first-page":"4765","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Abnar, S., and Zuidema, W. (2020, January 5\u201310). Quantifying Attention Flow in Transformers. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Virtual.","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., and Wolf, L. (2021, January 20\u201325). Transformer Interpretability Beyond Attention Visualization. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"16022","DOI":"10.1038\/s41598-024-66989-9","article-title":"Enhancing Agriculture through Real-Time Grape Leaf Disease Classification via an Edge Device with a Lightweight CNN Architecture and Grad-CAM","volume":"14","author":"Karim","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"156038","DOI":"10.1109\/ACCESS.2024.3484574","article-title":"Plant Leaf Disease Detection Using Ensemble Learning and Explainable AI","volume":"12","author":"Ammar","year":"2024","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2942","DOI":"10.1080\/01140671.2025.2519570","article-title":"Hybrid Deep Learning Model for Maize Leaf Disease Classification with Explainable AI","volume":"53","author":"Alpsalaz","year":"2025","journal-title":"N. Z. J. Crop Hortic. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Peyal, H.I., Mondal, N.I.M., and Miraz, S. (2024). An Efficient Explainable AI Method Combining CNN and SVM for Corn Leaf Disease Detection and Visualization. 2024 27th International Conference on Computer and Information Technology (ICCIT), Cox\u2019s Bazar, Bangladesh, 20\u201322 December 2024, IEEE.","DOI":"10.1109\/ICCIT64611.2024.11021795"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., Magno, M., Benini, L., and Van Goo, L. (2023, January 1\u20135). LocalViT: Analyzing Locality in Vision Transformers. Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Detroit, MI, USA.","DOI":"10.1109\/IROS55552.2023.10342025"},{"key":"ref_28","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., and Girshick, R. (2021, January 6\u201314). Early Convolutions Help Transformers See Better. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual. Available online: https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/ff1418e8cc993fe8abcfe3ce2003e5c5-Paper.pdf."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"15","DOI":"10.4316\/JACSM.202101002","article-title":"Maize Leaf Disease Detection Using Convolutional Neural Networks","volume":"15","author":"Micheni","year":"2021","journal-title":"J. Appl. Comput. Sci. Math."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhu, T., Yan, F., Lv, X., Zhao, H., Wang, Z., Dong, K., Fu, Z., Jia, R., and Lv, C. (2024). A Deep Learning Model for Accurate Maize Disease Detection Based on State-Space Attention and Feature Fusion. Plants, 13.","DOI":"10.3390\/plants13223151"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, X., Lin, J., Pan, R., Cao, T., Cai, J., Yu, D., Cernava, T., and Zhang, X. (2022). DFCANet: A Novel Lightweight Convolutional Neural Network Model for Corn Disease Identification. Agriculture, 12.","DOI":"10.3390\/agriculture12122047"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Gopalan, K., Srinivasan, S., Pragya, P., Singh, M., Mathivanan, S.K., and Moorthy, U. (2025). Corn Leaf Disease Diagnosis: Enhancing Accuracy with Resnet152 and Grad-Cam for Explainable AI. BMC Plant Biol., 25.","DOI":"10.1186\/s12870-025-06386-0"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"105412","DOI":"10.1016\/j.chemolab.2025.105412","article-title":"Classification of Maize Leaf Diseases with Deep Learning: Performance Evaluation of the Proposed Model and Use of Explicable Artificial Intelligence","volume":"262","author":"Alpsalaz","year":"2025","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_34","first-page":"214","article-title":"Hybrid Adaptive Swarm Enhanced Vision Transformer for Accurate Corn Leaf Disease Prediction","volume":"21","author":"Patil","year":"2026","journal-title":"Fusion Pract. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1007\/s44163-025-00548-7","article-title":"A Statistically Validated Stacking Ensemble of CNNs and Vision Transformer for Robust Maize Disease Classification","volume":"5","author":"Weldeslasie","year":"2025","journal-title":"Discov. Artif. Intell."},{"key":"ref_36","first-page":"3965","article-title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2397","DOI":"10.21037\/qims-21-919","article-title":"TransConver: Transformer and Convolution Parallel Network for Developing Automatic Brain Tumor Segmentation in MRI Images","volume":"12","author":"Liang","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_38","first-page":"e70655","article-title":"A Hybrid SwinTConvNeXt with Learnable Dynamic Gating Fusion for Breast Cancer Histopathology Image Classification","volume":"8","author":"Makina","year":"2026","journal-title":"Eng. Rep."},{"key":"ref_39","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_40","first-page":"8368","article-title":"Depthwise Convolution Is All You Need for Learning Multiple Visual Domains","volume":"33","author":"Guo","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_41","unstructured":"Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer Normalization. arXiv."},{"key":"ref_42","unstructured":"Gupta, A., Ozdemir, A., and Anumanchipalli, G. (2025). Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm. arXiv."},{"key":"ref_43","unstructured":"Ahmad, A., Saraswat, D., El Gamal, A., and Johal, G. (2021). CD&S Dataset: Handheld Imagery Dataset Acquired Under Field Conditions for Corn Disease Identification and Severity Estimation. arXiv."},{"key":"ref_44","unstructured":"Ghose, S. (2025, July 10). Corn or Maize Leaf Disease Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/smaranjitghose\/corn-or-maize-leaf-disease-dataset."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Waema, D., Mwangi, W., and Muriithi, P. (2025, January 28\u201330). A Min-Max Based Data Normalization and Maximum Pooling Approach for Improved Maize Leaf Disease Detection. Proceedings of the 2025 IST-Africa Conference (IST-Africa), Nairobi, Kenya.","DOI":"10.23919\/IST-Africa67297.2025.11060470"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.procs.2018.01.028","article-title":"Training with Noise Addition in Neural Network Solution of Inverse Problems: Procedures for Selection of the Optimal Network","volume":"123","author":"Isaev","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_47","first-page":"3","article-title":"Tiny ImageNet Visual Recognition Challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"}],"container-title":["Plants"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2223-7747\/15\/6\/982\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T14:16:27Z","timestamp":1774275387000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2223-7747\/15\/6\/982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":47,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["plants15060982"],"URL":"https:\/\/doi.org\/10.3390\/plants15060982","relation":{},"ISSN":["2223-7747"],"issn-type":[{"value":"2223-7747","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]}}}