# XAI and Few-shot-based Hybrid Classification Model for Plant Leaf Disease Prognosis

Source: [XAI and Few-shot-based Hybrid Classification Model for Plant Leaf Disease Prognosis](<https://www.sota2.com/research/paper/69afa57e2d603e6de3e439f0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-11T05:00:04.181Z

Authors: Diana Susan Joseph, Pranav M Pawar, Raja Muthalagu, Mithun Mukharjee

Published: 2026-03-03T13:29:35.000Z

## Abstract

Performing a timely and accurate identification of crop diseases is vital to maintain agricultural productivity and food security. The current work presents a hybrid few-shot learning model that integrates Explainable Artificial Intelligence (XAI) and Few-Shot Learning (FSL) to address the challenge of identifying and classifying the stages of disease of the diseases of maize, rice, and wheat leaves under limited annotated data conditions. The proposed model integrates Siamese and Prototypical Networks within an episodic training paradigm to effectively learn discriminative disease features from a few examples. To ensure model transparency and trustworthiness, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed for visualizing key decision regions in the leaf images, offering interpretable insights into the classification process. Experimental evaluations on custom few-shot datasets developed in the study prove that the model consistently achieves high accuracy, precision, recall, and F1-scores, frequently exceeding 92% across various disease stages. Comparative analyses against baseline FSL models further confirm the superior performance and explainability of the proposed approach. The framework offers a promising solution for real-world, data-constrained agricultural disease monitoring applications.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on Plant Leaf Datasets Few-shot Rice Bacterial Blight (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-rice-bacterial-blight-val.md>): Image Classification; Plant Leaf Datasets Few-shot Rice Bacterial Blight (val); Validation Accuracy: 97.5.

- [Image Classification on Few-shot Plant Leaf Datasets Rice Bacterial Leaf Streak (val)](<https://www.sota2.com/research/sota/image-classification-on-few-shot-plant-leaf-datasets-rice-bacterial-leaf-streak-val.md>): Image Classification; Few-shot Plant Leaf Datasets Rice Bacterial Leaf Streak (val); Accuracy: 97.5.

- [Image Classification on Plant Leaf Datasets Few-shot Rice Blast (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-rice-blast-val.md>): Image Classification; Plant Leaf Datasets Few-shot Rice Blast (val); Accuracy: 97.5.

- [Image Classification on Few-shot Plant Leaf Datasets Rice Brown Spot (val)](<https://www.sota2.com/research/sota/image-classification-on-few-shot-plant-leaf-datasets-rice-brown-spot-val.md>): Image Classification; Few-shot Plant Leaf Datasets Rice Brown Spot (val); Accuracy: 97.5.

- [Image Classification on Plant Leaf Datasets Few-shot Wheat Leaf Rust (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-wheat-leaf-rust-val.md>): Image Classification; Plant Leaf Datasets Few-shot Wheat Leaf Rust (val); Accuracy: 95.5.

- [Image Classification on Plant Leaf Datasets Few-shot Wheat Powdery Mildew (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-wheat-powdery-mildew-val.md>): Image Classification; Plant Leaf Datasets Few-shot Wheat Powdery Mildew (val); Validation Accuracy: 95.5.

- [Image Classification on Plant Leaf Datasets Few-shot Wheat Stripe Rust (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-wheat-stripe-rust-val.md>): Image Classification; Plant Leaf Datasets Few-shot Wheat Stripe Rust (val); Validation Accuracy: 97.5.

- [Image Classification on Plant Leaf Datasets Few-shot Wheat Tan Spot (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-wheat-tan-spot-val.md>): Image Classification; Plant Leaf Datasets Few-shot Wheat Tan Spot (val); Accuracy: 97.5.

- [Image Classification on Plant Leaf Datasets Maize Common Rust Few-shot (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-maize-common-rust-few-shot-val.md>): Image Classification; Plant Leaf Datasets Maize Common Rust Few-shot (val); Validation Accuracy: 92.5.

- [Image Classification on Few-shot Plant Leaf Datasets Maize Grey Leaf Spot (val)](<https://www.sota2.com/research/sota/image-classification-on-few-shot-plant-leaf-datasets-maize-grey-leaf-spot-val.md>): Image Classification; Few-shot Plant Leaf Datasets Maize Grey Leaf Spot (val); Accuracy (val): 97.5.

- [Image Classification on Plant Leaf Datasets Maize Northern Leaf Blight Few-shot (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-maize-northern-leaf-blight-few-shot-val.md>): Image Classification; Plant Leaf Datasets Maize Northern Leaf Blight Few-shot (val); Accuracy: 97.5.

- [Image Classification on Plant Leaf Datasets Few-shot Maize Southern Rust (val)](<https://www.sota2.com/research/sota/image-classification-on-plant-leaf-datasets-few-shot-maize-southern-rust-val.md>): Image Classification; Plant Leaf Datasets Few-shot Maize Southern Rust (val); Validation Accuracy: 92.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.06676>)

[PDF](<https://arxiv.org/pdf/2603.06676.pdf>)
