A Domain-Adapted Lightweight Ensemble for Resource-Efficient Few-Shot Plant Disease Classification

TL;DR

This paper introduces a lightweight, domain-adapted ensemble model for resource-efficient few-shot plant disease classification, achieving high accuracy with minimal data and computational resources suitable for real-world agricultural settings.

Contribution

It presents a novel combination of lightweight MobileNet models with a Bi-LSTM classifier and attention, optimized for few-shot plant disease detection in resource-constrained environments.

Findings

Achieves 98.23% accuracy on Tomato leaf diseases with 15-shot learning.

Maintains robust performance in real-world field conditions.

Outperforms previous state-of-the-art with 99.72% accuracy on PlantVillage dataset.

Abstract

Accurate and timely identification of plant leaf diseases is essential for resilient and sustainable agriculture, yet most deep learning approaches rely on large annotated datasets and computationally intensive models that are unsuitable for data-scarce and resource-constrained environments. To address these challenges we present a few-shot learning approach within a lightweight yet efficient framework that combines domain-adapted MobileNetV2 and MobileNetV3 models as feature extractors, along with a feature fusion technique to generate robust feature representation. For the classification task, the fused features are passed through a Bi-LSTM classifier enhanced with attention mechanisms to capture sequential dependencies and focus on the most relevant features, thereby achieving optimal classification performance even in complex, real-world environments with noisy or cluttered backgrounds. The proposed framework was evaluated across multiple experimental setups, including both laboratory-controlled and field-captured datasets. On tomato leaf diseases from the PlantVillage dataset, it consistently improved performance across 1 to 15 shot scenarios, reaching 98.23+-0.33% at 15 shot, closely approaching the 99.98% SOTA benchmark achieved by a Transductive LSTM with attention, while remaining lightweight and mobile-friendly. Under real-world conditions using field images from the Dhan Shomadhan dataset, it maintained robust performance, reaching 69.28+-1.49% at 15-shot and demonstrating strong resilience to complex backgrounds. Notably, it also outperformed the previous SOTA accuracy of 96.0% on six diseases from PlantVillage, achieving 99.72% with only 15-shot learning. With a compact model size of approximately 40 MB and inference complexity of approximately 1.12 GFLOPs, this work establishes a scalable, mobile-ready foundation for precise plant disease diagnostics in data-scarce regions.