Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning techniques trained solely on synthetic data encounter dramatic performance drops when they are tested on real data. Such performance drop is commonly attributed to the domain gap between real and synthetic data. Domain adaptation methods have been applied to mitigate the aforementioned domain gap. These methods achieve visually appealing results, but the translated samples usually introduce semantic inconsistencies. In this work, we propose a new, unsupervised, end-to-end domain adaptation network architecture that enables semantically consistent domain adaptation between synthetic and real data. We evaluate our architecture on the downstream task of semantic segmentation and show that our method achieves superior performance compared to the state-of-the-art methods.
翻译:合成数据生成是一种具有吸引力的方法,在自主驾驶中生成新的交通情况。然而,在对合成数据进行测试时,仅接受过合成数据培训的深层次学习技术在性能上遇到显著下降。这种性能下降通常归因于真实数据和合成数据之间的领域差距。应用了域适应方法来缩小上述领域差距。这些方法取得了有视觉吸引力的结果,但翻译的样本通常会引入语义不一致。在这项工作中,我们提出了一个新的、不受监督的、端对端域适应网络架构,使合成数据与真实数据之间能够进行语义上一致的域适应。我们评估了我们关于下游语义分割任务的架构,并表明我们的方法与最新方法相比取得了优异的性能。