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

Source: [Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning](<https://www.sota2.com/research/paper/69c60ef30636e5bf4afc8431>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-28T05:00:04.914Z

Authors: Md. Rokon Mia, Rakib Hossain Sajib, Abdullah Al Noman, Abir Ahmed, B M Taslimul Haque

Published: 2026-03-26T04:07:08.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Leaf Disease Classification on Rice Leaf Images](<https://www.sota2.com/research/sota/leaf-disease-classification-on-rice-leaf-images.md>): Leaf Disease Classification; Rice Leaf Images; Accuracy: 99.6.

- [Leaf Disease Classification on Wheat Leaf Dataset](<https://www.sota2.com/research/sota/leaf-disease-classification-on-wheat-leaf-dataset.md>): Leaf Disease Classification; Wheat Leaf Dataset; Accuracy: not recorded.

- [leaf disease classification on Rice Leaf Dataset UCI](<https://www.sota2.com/research/sota/leaf-disease-classification-on-rice-leaf-dataset-uci.md>): Leaf Disease Classification; Rice Leaf Dataset UCI; Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.25006>)

[PDF](<https://arxiv.org/pdf/2603.25006.pdf>)
