Handling imbalance and few-sample size in ML based Onion disease classification

2025-09-01

AI Summary

To address low classification accuracy and poor generalization in onion pest and disease multiclass recognition—caused by severe class imbalance and limited labeled samples—this paper proposes a CNN framework integrating channel-spatial attention mechanisms with systematic deep data augmentation. A lightweight attention module is embedded into a pretrained ResNet backbone to enhance discriminative feature representation from critical disease regions. Furthermore, we synergistically combine Mixup and CutMix with field-adapted geometric and photometric augmentations to achieve class-balanced training and improved semantic robustness. Evaluated on a real-world field image dataset, the proposed model achieves 96.90% overall accuracy and an F1-score of 0.96—substantially outperforming existing binary-classification and conventional multiclass approaches. This work delivers a high-accuracy, generalizable, small-sample solution for intelligent crop disease diagnosis.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Representation, semantic annotation, enhancement, enrichments, access and/or integration of a variety of data on the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate classification of pests and diseases plays a vital role in precision agriculture, enabling efficient identification, targeted interventions, and preventing their further spread. However, current methods primarily focus on binary classification, which limits their practical applications, especially in scenarios where accurately identifying the specific type of disease or pest is essential. We propose a robust deep learning based model for multi-class classification of onion crop diseases and pests. We enhance a pre-trained Convolutional Neural Network (CNN) model by integrating attention based modules and employing comprehensive data augmentation pipeline to mitigate class imbalance. We propose a model which gives 96.90% overall accuracy and 0.96 F1 score on real-world field image dataset. This model gives better results than other approaches using the same datasets.

Problem

• Addressing class imbalance in multi-class onion disease classification
• Improving few-sample learning for agricultural pest identification
• Enhancing CNN accuracy with attention modules and data augmentation

Innovation

• Attention-enhanced CNN for multi-class disease classification
• Comprehensive data augmentation to address class imbalance
• Achieves 96.9% accuracy on real-world field images