arXiv cs.AI· Hicham El Akhal, Abderrahim Waga, Aissa Ben Yahya, Abdelbaki El Belrhiti El Alaoui·· 2 小时前AI 评分22
数据生成策略如何提升深度模型在橄榄树病害分类中的表现
Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases
AI 导读
一项研究提出综合数据生成策略，结合传统增强、CutMix、MixUp 与 DCGAN 合成图像，缓解植物病害诊断中数据不足和类别不平衡问题。研究将生成数据用于三种场景（S1 平衡类别、S2 增加每类样本、S3 扩充数据集并保持平衡），并用预训练与微调的 EfficientNetV2B0 评估影响。结果显示分类准确率显著提升，凸显数据多样性与类别平衡的关键作用。
正文 · 原文
Abstract:Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generation using Deep Convolu tional Generative Adversarial Networks (DCGANs), to create new data samples. Second, we exploit this generated data in three scenarios: (S1) balancing class distribution in the original dataset, (S2) increasing the number of samples per class, and (S3) expanding the dataset while maintaining balanced classes. Third, we evaluate the impact of these data distributions (S1, S2, S3) on model perfor mance using the EfficientNetV2B0 architecture with pre-trained and fine-tuned weights. The experimental results show a substantial improvement in classifica tion accuracy, emphasizing the critical role of data diversity and class balance. These findings highlight the effectiveness and adaptability of the proposed strat egy of data generation and distribution for enhancing dataset quality, offering promising applications in plant disease detection and precision agriculture.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35984 [cs.AI] |
| (or arXiv:2610.35984v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35984 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abderrahim Waga [view email]
[v1]
Mon, 26 Oct 2026 11:53:49 UTC (2,970 KB)
来源：arXiv cs.AI · arxiv.org