Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning

TL;DR

This paper introduces a dual-loss framework combining Center Loss and ArcFace Loss to improve fine-grained rice leaf disease classification, achieving high accuracy across multiple neural network architectures.

Contribution

The novel dual-loss approach enhances discriminative feature learning for rice disease detection without major architecture changes.

Findings

Achieved over 99% accuracy on rice leaf disease dataset.

Dual-loss framework outperforms traditional cross entropy loss.

Effective across multiple backbone architectures.

Abstract

Early detection of rice leaf diseases is critical, as rice is a staple crop supporting a substantial share of the world's population. Timely identification of these diseases enables more effective intervention and significantly reduces the risk of large-scale crop losses. However, traditional deep learning models primarily rely on cross entropy loss, which often struggles with high intra-class variance and inter-class similarity, common challenges in plant pathology datasets. To tackle this, we propose a dual-loss framework that combines Center Loss and ArcFace Loss to enhance fine-grained classification of rice leaf diseases. The method is applied into three state-of-the-art backbone architectures: InceptionNetV3, DenseNet201, and EfficientNetB0 trained on the public Rice Leaf Dataset. Our approach achieves significant performance gains, with accuracies of 99.6%, 99.2% and 99.2% respectively. The results demonstrate that angular margin-based and center-based constraints substantially boost the discriminative strength of feature embeddings. In particular, the framework does not require major architectural modifications, making it efficient and practical for real-world deployment in farming environments.