arXiv cs.AI· Hicham El Akhal, Abderrahim Waga, Aissa Ben Yahya, Abdelbaki El Belrhiti El Alaoui·· 11 小时前AI 评分18
通过数据生成策略提升深度学习模型性能：橄榄树病害分类
Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases
AI 导读
研究提出一套数据生成策略，结合传统增强方法、CutMix、MixUp 与 DCGAN 合成图像生成新样本，并在平衡类别分布、增加每类样本数、扩充数据集同时保持类别平衡三种场景下使用生成数据。基于预训练并微调的 EfficientNetV2B0 架构评估显示，分类准确率大幅提升，凸显数据多样性与类别平衡的关键作用。
正文
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