发表机构
University of Calgary（卡尔加里大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究合成数据和标签分布对油菜分枝计数的影响，通过校准的L系统植物模型训练ResNet - 18模型，独立改变合成与真实图像比例及标签分布，发现不同比例和分布对性能有不同影响，得出最佳参数和简单替代方案。
AI 中文摘要
收集带注释的植物图像用于自动表型分析通常既缓慢又昂贵。模拟生长发育的植物模型可以生成带有精确标签的无限合成图像。然而，先前的研究表明，纳入合成数据是否能提高性能取决于合成图像与真实图像的比例以及合成数据集的标签分布。为了系统地量化这两个因素，我们使用校准的L系统植物模型在油菜分枝计数任务上训练ResNet - 18模型。我们独立改变每个因素。合成与真实图像比例在1:5到1:22之间时性能普遍提高；最佳比例（1:7）相比仅使用真实数据训练，平均绝对差降低了7.6%。对于标签分布，均匀的合成分布效果很差（绝对差约为1.70）；向真实分布插值90%时绝对差为0.927，而对真实标签分布进行高斯平滑得到最佳总体结果（绝对差0.912，相比仅使用真实数据提高了14.7%）。每个标签最少10张合成图像是一种有适度提升的简单替代方案，而每个标签100张则会过度校正并损害性能。
英文摘要
Collecting annotated plant images for automated phenotyping is often slow and expensive. Plant models simulating growth and development can generate unlimited synthetic images with exact labels. However, previous work has established that whether incorporating synthetic data improves performance depends on the ratio of synthetic to real images and the label distribution of the synthetic dataset. To systematically quantify both factors, we train ResNet-18 models on a canola branch-counting task using a calibrated L-system plant model. We vary each factor independently. Synthetic-to-real ratios of 1:5 to 1:22 broadly improve performance; the best ratio (1:7) reduces mean absolute difference by 7.6% over real-only training. For label distribution, a uniform synthetic distribution is strongly suboptimal (abs. diff. of approximately 1.70); interpolating 90% toward the real distribution yields abs. diff. 0.927, whereas Gaussian smoothing of the real label distribution yields the best overall result (abs. diff. 0.912, a 14.7% improvement over real-only). A minimum of 10 synthetic images per label offers a simpler alternative with modest gains, while 100 per label over-corrects and hurts performance.
Comments5 pages, 4 figures, submitted to EPA 2026
