BMC Plant Biology· 2026Q1
A field-acquired annotated dataset for robust and generalizable pomegranate disease detection using generative learning
- 0citations
- Q1SCImago
- 2026year
Short summary
A novel Dual GAN–Diffusion generative learning system created diverse, realistic pomegranate disease images, improving classification accuracy to 76% and outperforming baseline GANs.
AI-generated from the title and abstract; the full text is not read.
Key points
- A Dual GAN–Diffusion generative learning system was developed to create synthetic images for pomegranate disease detection.
- The system achieved strong image quality and diversity metrics (FID: 22.40, IS: 49.75, LPIPS Diversity: 69.86%).
- Pomegranate disease classification accuracy improved to 76% using the generated dataset, surpassing baseline GAN models.
- The approach enhances the scalability and reliability of disease detection in real-world agricultural environments.
AI-generated from the title and abstract; the full text is not read.
Abstract
Pomegranates are popular in India for their health benefits and high levels of antioxidants and vitamins. Detecting diseases in pomegranates is important for maintaining their quality. However, inconsistent dataset annotations and challenging field conditions make it difficult to collect high-quality images, limiting deep learning model performance. To address this, we introduce a Dual GAN–Diffusion-based generative learning system that creates high-quality, diverse images to improve pomegranate disease datasets. We collect and process real-time data using a GAN to generate diverse and realistic images for detecting and diagnosing pomegranate diseases. With a Fr´echet Inception Distance (FID) of 22.40, Inception Score (IS) of 49.75, LPIPS Diversity of 69.86%, and classification Accuracy of 76%, the perform The system achieved a Fr´echet Inception Distance (FID) of 22.40, Inception Score (IS) of 49.75, LPIPS Diversity of 69.86%, and classification accuracy of 76%. These results show clear improvements over baseline GAN models. This will show that our research approach can generate diverse, realistic samples, improve the system, and make healthy and diseased classification more scalable and reliable in real-world agricultural settings.
The authors' abstract, as published at the source. BMC Plant Biology, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Nutrition and Dietetics
Nutrition and DieteticsNursing