Skip to content
F~Agtech

LightTeaNet: SeparableConv-based lightweight CNN with Grad-CAM explainability for tea leaf disease identification

The Combine·15h ago·3 views
Authors: Sarker MR, Al-Faruk J, Fatema K, Das J, Saju MS, Akhi OJField: PloS oneYear: 2026DOI: 10.1371/journal.pone.0363128

Global tea production, valued at USD 25.6 billion in 2024, faces annual yield losses of approximately 20% due to foliar diseases, yet existing deep learning-based detection systems remain impractical for real-world deployment due to prohibitive computational requirements and limited interpretability. This paper presents a purpose-built lightweight convolutional neural network architecture for four-class tea leaf disease classification (Brown Blight, Red Rust, Red Spider Mite, and Healthy Leaves) that achieves an exceptional balance between classification accuracy and computational efficiency. The proposed model leverages depthwise separable convolutions across four progressive feature extraction blocks, integrated with Batch Normalization, Global Average Pooling, and Dropout regularization to minimize parameter count while maintaining discriminative feature learning. Evaluated on the TeaLeafNet dataset (5,000 balanced images across four categories), the model achieves 98.14% classification accuracy with only 80,959 trainable parameters-representing a 90-fold reduction compared to DenseNet121 (7.3M parameters)-and a model size of merely 0.31 MB, while requiring only 191.29 million FLOPs, approximately 160 × fewer than VGG16 (30.71B FLOPs). The model demonstrates robust per-class performance with F1-scores of 0.97 or higher across all categories and perfect ROC-AUC values of 1.000 for two classes. Grad-CAM visualization, validated through quantitative Insertion (AUC: 0.972) and Deletion (AUC: 0.181) faithfulness evaluation, confirms that the model's predictions are driven by diagnostically relevant leaf regions, achieving model transparency essential for agricultural adoption. Comparative analysis against nine state-of-the-art architectures-including DenseNet121, MobileNetV2, ResNet50, and EfficientNetB1-reveals that while DenseNet121 achieves marginally higher accuracy (99.20%), it requires 90 × more parameters and 30 × more computational operations, rendering it uns…

View external link ↗ (opens in a new tab)
Score: 0

0 Comments

The summary above is machine-written and the abstract is the authors' own pitch. This is where people who read the paper say what it actually found, what the summary missed, and which part is worth your time.

Log in to join the discussion.