Clustering-Guided Multi-Layer Contrastive Representation Learning for Citrus Disease Classification

2025-07-15

AI Summary

In citrus disease classification, challenges include scarcity of high-quality labeled samples, high visual similarity among disease symptoms, severe class imbalance, and limitations of existing deep learning methods in effectively leveraging unlabeled data and learning hierarchical features. To address these issues, this paper proposes a clustering-guided self-supervised multi-level contrastive representation learning framework. Our method jointly optimizes clustering-center contrast and multi-layer feature-space contrast to achieve hierarchical semantic representation learning in a fully unsupervised manner. Evaluated on the CDD dataset, the proposed approach achieves accuracy improvements of 4.5–30.1% over state-of-the-art methods; it also significantly outperforms prior work in F1-score, precision, and recall. Moreover, it demonstrates strong robustness to label noise and class imbalance, substantially narrowing the performance gap between self-supervised and fully supervised paradigms.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Citrus, as one of the most economically important fruit crops globally, suffers severe yield depressions due to various diseases. Accurate disease detection and classification serve as critical prerequisites for implementing targeted control measures. Recent advancements in artificial intelligence, particularly deep learning-based computer vision algorithms, have substantially decreased time and labor requirements while maintaining the accuracy of detection and classification. Nevertheless, these methods predominantly rely on massive, high-quality annotated training examples to attain promising performance. By introducing two key designs: contrasting with cluster centroids and a multi-layer contrastive training (MCT) paradigm, this paper proposes a novel clustering-guided self-supervised multi-layer contrastive representation learning (CMCRL) algorithm. The proposed method demonstrates several advantages over existing counterparts: (1) optimizing with massive unannotated samples; (2) effective adaptation to the symptom similarity across distinct citrus diseases; (3) hierarchical feature representation learning. The proposed method achieves state-of-the-art performance on the public citrus image set CDD, outperforming existing methods by 4.5%-30.1% accuracy. Remarkably, our method narrows the performance gap with fully supervised counterparts (all samples are labeled). Beyond classification accuracy, our method shows great performance on other evaluation metrics (F1 score, precision, and recall), highlighting the robustness against the class imbalance challenge.

Problem

• Improving citrus disease classification accuracy with limited labeled data
• Addressing symptom similarity across different citrus diseases
• Enhancing hierarchical feature representation learning for disease detection

Innovation

• Clustering-guided multi-layer contrastive representation learning
• Contrasting with cluster centroids design
• Multi-layer contrastive training paradigm