Explainable lightweight deep learning architectures for crop anomaly detection using enhanced Grad-CAM and transfer learning

Authors

References

Ngoune Liliane T Shelton Charles M. 'Factors Affecting Yield of Crops ' Agronomy - Climate Change and Food Security. IntechOpen. 2020. doi: 10.5772/intechopen.90672.

Rohach Y Yatsukh O Zoria M. Determining the risks of the production environment of an agricultural enterprise. In: Modern Development Paths of Agricultural Production: Trends and Innovations. Springer: Cham Switzerland; 2019. p. 777–783. doi: 10.1007/978-3-030-14918-5_76

https://doi.org/10.1038/s41559-018-0793-y

https://doi.org/10.1016/j.gfs.2017.01.011

https://doi.org/10.1016/J.JENVMAN.2021.111949

https://doi.org/10.1039/D4RA02310B

https://doi.org/10.1109/ACCESS.2024.3397619

https://doi.org/10.56557/pcbmb/2024/v25i11-128918

https://doi.org/10.1109/JIOT.2018.2879579

https://doi.org/10.1371/JOURNAL.PONE.0324347

https://doi.org/10.3389/FPLS.2022.837726/BIBTEX

https://doi.org/10.1007/S10460-022-10374-7/FIGURES/10

https://doi.org/10.1016/J.FOCHX.2025.102748

https://doi.org/10.1109/ACCESS.2023.3345789

https://doi.org/10.1016/j.atech.2024.100718

https://doi.org/10.1016/j.inpa.2025.02.004

Bauravindah A Fudholi DH. Lightweight Models for Real-Time Steganalysis: A Comparison of MobileNet ShuffleNet and EfficientNet. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 2024;8(6): 737–747. doi: 10.29207/resti.v8i6.6091

https://doi.org/10.1038/S41598-025-94083-1;SUBJMETA

https://doi.org/10.1038/S41598-024-66989-9;SUBJMETA

https://doi.org/10.1186/s12870-025-06386-0

https://doi.org/10.1007/S12161-025-02892-X/METRICS

https://doi.org/10.3389/FPLS.2020.00510/BIBTEX

https://doi.org/10.1016/j.atech.2025.101409

https://doi.org/10.1007/978-3-031-35314-7_2

https://doi.org/10.1007/s10462-024-10877-1

Rane J Mallick SK Kaya O et al. Enhancing black-box models: Advances in explainable artificial intelligence for ethical decision-making. In: Future Research Opportunities for Artificial Intelligence in Industry 4.0 and 5.0. Deep Science Publishing; 2024. pp. 136–180

https://doi.org/10.1016/j.atech.2025.100817

https://doi.org/10.1016/j.compag.2024.109865

https://doi.org/10.3390/agriengineering6030117

https://doi.org/10.1007/s11540-026-10033-y

https://doi.org/10.1186/S12870-026-08341-Z

https://doi.org/10.1186/s12864-019-6413-7

https://doi.org/10.1016/j.patrec.2019.10.004

https://doi.org/10.1038/s41598-025-02271-w

https://doi.org/10.1016/j.eja.2025.127625

https://doi.org/10.1038/s41598-025-93742-7

https://doi.org/10.1016/j.neucom.2024.128791

Sunil CK Jaidhar CD Patil N Cardamom plant disease detection approach using EfficientNetV2. IEEE Access. 2022;10:789–804. doi: 10.1109/ACCESS.2021.3138920

Pradhan NR Ghosh H Rahat IS et al. Enhancing agricultural sustainability with deep learning: A case study of cauliflower disease classification. EAI Endorsed Transactions on Internet of Things. 2024;10. doi: 10.4108/eetiot.4834

https://doi.org/10.1007/S11042-022-13673-7/METRICS

Olayiwola JO Adejoju JA. Maize (corn) leaf disease detection system using convolutional neural network (CNN). In: International Conference on Computational Science and Its Applications. 2023 p. 309–321.

https://doi.org/10.1016/j.ecoinf.2022.101663

Vikhe BB, Patil PR, Bhaladhare PR, et al. Image-based onion leaf disease identification using a CNN-Transformer hybrid approach. Int J Image Data Fusion. 2025;16(1):2561938.

https://doi.org/10.3390/plants10122643

https://doi.org/10.1016/j.aiia.2023.07.001

Narkhede J. Comparative evaluation of post-hoc explainability methods in AI: lime shap and Grad-CAM. In: 2024 4th International Conference on Sustainable Expert Systems (ICSES) 2024. p. 826–830. doi: 10.1109/ICSES63445.2024.10762963.

Yoon HC Lin LP Brain tumor classification in MRI: Insights from LIME and Grad-CAM explainable AI techniques. IEEE Access. 2025;13:154172–154202. doi: 10.1109/ACCESS.2025.3603272

https://doi.org/10.1016/j.atech.2025.101348

https://doi.org/10.1038/s41598-025-14306-3

Cited By (0)

No indexed citing article has been matched by IRCI yet.