Call For Paper November 2026
Research Article | Open Access | Download PDF
Volume 13 | Issue 10 | Year 2026 | Article Id. IJECE-V13I10P103 | DOI : https://doi.org/10.14445/23488549/IJECE-V13I10P103

Reliability-Aware Explainability for Rice Leaf Disease Classification: Weak Localization, Cross-XAI Comparison, and Cross-Source Generalization

Sujeet Kumar, Prajeet Sharma

Received Revised Accepted Published
24 Aug 2026 15 Sep 2026 18 Sep 2026 28 Oct 2026

Citation :

Sujeet Kumar, Prajeet Sharma, "Reliability-Aware Explainability for Rice Leaf Disease Classification: Weak Localization, Cross-XAI Comparison, and Cross-Source Generalization," International Journal of Electronics and Communication Engineering, vol. 13, no. 10, pp. 36-53, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I10P103

Abstract

This study presents a reliability-oriented framework for evaluating whether high classification performance in rice leaf disease recognition is accompanied by spatially faithful and generalizable explanations. The primary dataset comprised 4,684 images from three disease classes: bacterial blight, brown spot, and leaf smut. Perceptual-hash grouping and group-preserving partitioning were applied to reduce duplicate-related data leakage, and three ImageNet-pretrained residual networks were evaluated under a common training protocol. ResNet50 achieved the highest observed held-out performance, with an accuracy of 0.9968 and macro-F1 of 0.9967. Explanation reliability was evaluated using a 286-image Mini-GT benchmark with lesion-level bounding boxes, together with localization metrics, calibration analysis, perturbation robustness, and threshold sensitivity. Despite perfect classification on this evaluation subset, Grad-CAM++ produced limited localization, with a mean IoU of 0.1831 and pointing-game accuracy of 0.4720. A comparative evaluation of six XAI methods found no significant overall difference in paired per-image IoU (Friedman χ²(5)=4.9796, p=0.4184), indicating that the observed localization limitation was not specific to Grad-CAM++. Independent cross-source evaluation on a non-overlapping 120-image dataset yielded an accuracy of 0.5667 (95% CI: 0.4773–0.6519) and macro-F1 of 0.5453, revealing substantial degradation in external generalization. Overall, the findings demonstrate that high internal classification performance does not necessarily imply reliable lesion localization, stable explanations across XAI methods, or strong cross-source generalization.

Keywords

Rice leaf disease, Explainable Artificial Intelligence, Weak localization, XAI reliability, Lesion localization, Cross-source generalization, Precision agriculture.

References

  1. David. P. Hughes, and Marcel Salathe, “An Open Access Repository of Images on Plant Health to Enable the Development of Mobile Disease Diagnostics through Machine Learning and Crowdsourcing,” arXiv preprint, pp. 1-13, 2015.
    [    CrossRef] [Google Scholar] [Publisher Link]
  2. Sharada P. Mohanty, David P. Hughes, and Marcel Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, pp. 1-10, 2016.
    [    CrossRef] [Google Scholar] [Publisher Link]
  3. Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
    [    CrossRef] [Google Scholar] [Publisher Link]
  4. Ramprasaath R. Selvaraju et al., “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 618-626, 2017.
    [    CrossRef] [Google Scholar] [Publisher Link]
  5. Aditya Chattopadhay et al., “Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks,” 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, pp. 839-847, 2018.
    [    CrossRef] [Google Scholar] [Publisher Link]
  6. Chih-Kuan Yeh et al., “On the (in) Fidelity and Sensitivity of Explanations,” Advances in Neural Information Processing Systems, vol. 32, 2019.
    [    Google Scholar] [Publisher Link]
  7. Ashkan Khakzar et al., “Do Explanations Explain? Model Knows Best,” 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 10244-10253, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  8. Chuan Guo et al., “On Calibration of Modern Neural Networks,” Proceedings of the 34th International Conference on Machine Learning, pp. 1321-1330, 2017.
    [    Google Scholar] [Publisher Link]
  9. Amit Dhurandhar et al., “Locally Invariant Explanations: Towards Stable and Unidirectional Explanations Through Local Invariant Learning,” Advances in Neural Information Processing Systems, vol. 36, pp. 19410-19445, 2023.
    [    Google Scholar] [Publisher Link]
  10. Chinna Gopi Simhadri et al., “Deep Learning for Rice Leaf Disease Detection: A Systematic Literature Review on Emerging Trends, Methodologies and Techniques,” Information Processing in Agriculture, vol. 12, no. 2, pp. 151-168, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  11. Shakti Kinger, and Vrushali Kulkarni, “Explainable AI for Deep Learning Based Disease Detection,” Proceedings of the 2021 Thirteenth International Conference on Contemporary Computing, pp. 209-216, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  12. Kaihua Wei et al., “Explainable Deep Learning Study for Leaf Disease Classification,” Agronomy, vol. 12, no. 5, pp. 1-15, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  13. Harshana Habaragamuwa, Yu Oishi, and Kenichi Tanaka, “Achieving Explainability for Plant Disease Classification with Disentangled Variational Autoencoders,” Engineering Applications of Artificial Intelligence, vol. 133, pp. 1-24, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  14. N. Krishnamoorthy et al., “Rice Leaf Diseases Prediction using Deep Neural Networks with Transfer Learning,” Environmental Research, vol. 198, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  15. P. Isaac Ritharson et al., “DeepRice: A Deep Learning and Deep Feature Based Classification of Rice Leaf Disease Subtypes,” Artificial Intelligence in Agriculture, vol. 11, pp. 34-49, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  16. Prameetha Pai et al., “A Twin CNN-Based Framework for Optimized Rice Leaf Disease Classification with Feature Fusion,” Journal of Big Data, vol. 12, no. 1, pp. 1-27, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  17. Junsuk Choe et al., “Evaluating Weakly Supervised Object Localization Methods Right,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 3133-3142, 2020.
    [    CrossRef] [Google Scholar] [Publisher Link]
  18. Jeesoo Kim et al., “Normalization Matters in Weakly Supervised Object Localization,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 3407-3416, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  19. Shakeeb Murtaza et al., “A Realistic Protocol for Evaluation of Weakly Supervised Object Localization,” 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, pp. 5367-5376, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  20. Wasswa Shafik et al., “Deep Learning Technique for Plant Disease Classification and Pest Detection and Model Explainability Elevating Agricultural Sustainability,” BMC Plant Biology, vol. 25, no. 1, pp. 1-31, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  21. Ruaa A. Al-Falluji, and Marwan Ali Albahar, “Enhancing Green AI Through Explainable Deep Learning-Based Multi-Model for Automated Rice Leaf Disease Classification,” Discover Computing, vol. 28, no. 1, pp. 1-26, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  22. Hyungsik Jung, and Youngrock Oh, “Towards Better Explanations of Class Activation Mapping,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 1336-1344, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  23. Sylvestre-Alvise Rebuffi et al., “There and Back Again: Revisiting Backpropagation Saliency Methods,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 8839-8848, 2020.
    [    CrossRef] [Google Scholar] [Publisher Link]
  24. Jianming Zhang et al., “Top-Down Neural Attention by Excitation Backprop,” International Journal of Computer Vision, vol. 126, no. 10, pp. 1084-1102, 2018.
    [    CrossRef] [Google Scholar] [Publisher Link]
  25. Aviral Kumar, Sunita Sarawagi, and Ujjwal Jain, “Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings,” Proceedings of the 35th International Conference on Machine Learning, pp. 2805-2814, 2018.
    [    Google Scholar] [Publisher Link]