Large data requirements are often the main hurdle in training neural networks. Convolutional neural network (CNN) classifiers in particular require tens of thousands of pre-labeled images per category to approach human-level accuracy, while often failing to generalized to out-of-domain test sets. The acquisition and labelling of such datasets is often an expensive, time consuming and tedious task in practice. Synthetic data provides a cheap and efficient solution to assemble such large datasets. Using domain randomization (DR), we show that a sufficiently well generated synthetic image dataset can be used to train a neural network classifier that rivals state-of-the-art models trained on real datasets, achieving accuracy levels as high as 88% on a baseline cats vs dogs classification task. We show that the most important domain randomization parameter is a large variety of subjects, while secondary parameters such as lighting and textures are found to be less significant to the model accuracy. Our results also provide evidence to suggest that models trained on domain randomized images transfer to new domains better than those trained on real photos. Model performance appears to remain stable as the number of categories increases.

大数据需求通常是训练神经网络的主要障碍。卷积神经网络 (CNN) 分类器尤其需要每个类别数以万计的预标记图像才能接近人类级别的准确度，但通常无法推广到域外测试集。在实践中，此类数据集的获取和标记通常是一项昂贵、耗时且乏味的任务。合成数据为组装如此大的数据集提供了一种廉价而有效的解决方案。使用域随机化 (DR)，我们表明生成足够好的合成图像数据集可用于训练神经网络分类器，该分类器可与在真实数据集上训练的最先进模型相媲美，实现高达 88% 的准确率基线猫与狗分类任务。我们表明，最重要的域随机化参数是种类繁多的主题，而诸如照明和纹理之类的次要参数对模型准确性的影响较小。我们的结果还提供证据表明，在域随机图像上训练的模型比在真实照片上训练的模型更好地转移到新域。随着类别数量的增加，模型性能似乎保持稳定。