Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4\% on an internal dataset and Dice scores of 79.6% and 83.6% on two external Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery.

翻译：深度学习模型已被广泛应用于各类图像处理任务。然而，这些模型大多通过监督学习方法开发，严重依赖大规模标注数据集的可用性。构建此类数据集既繁琐又昂贵。在缺乏标注数据集的情况下，合成数据可用于模型开发；但由于模拟数据与真实数据之间存在显著差异（即领域鸿沟现象），由此获得的模型在应用于真实数据时往往表现不佳。本研究旨在通过以下方法应对这一挑战：首先通过计算模拟生成大规模标注数据集，随后利用生成对抗网络（GAN）弥合模拟图像与真实图像之间的差距。该方法可生成训练深度学习模型所需的有效合成数据集。我们据此开发了用于麦穗分割的逼真标注合成数据集，并利用该数据集训练了语义分割深度学习模型。该模型在内部数据集上获得83.4%的Dice分数，在两个外部全球麦穗检测数据集上分别获得79.6%和83.6%的Dice分数。虽然本研究以麦穗分割为应用场景提出该方法，但其可推广至其他作物类型，或更广泛地应用于具有密集重复图案的图像（如细胞成像）。