Deep convolutional neural networks for semantic segmentation allow to achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization. In this paper, we introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. In particular, for this purpose we jointly enforce a clustering objective, a perpendicularity constraint and a norm alignment goal on the feature vectors corresponding to source and target samples. Additionally, we propose a novel measure able to capture the relative efficacy of an adaptation strategy compared to supervised training. We verify the effectiveness of such methods in the autonomous driving setting achieving state-of-the-art results in multiple synthetic-to-real road scenes benchmarks.

翻译：深卷动神经网络的语义分解可以实现突出的准确性,但是它们也有两大缺点:第一,它们并不全面,其分布与培训数据中的数据略有不同;第二,它们需要大量贴标签的数据才能优化。在本文件中,我们引入了地平层空间整形战略,以减少语义分解的域差异。特别是,为此目的,我们共同实施了组合目标、个性限制和与源和目标样本相对应的特征矢量的规范调整目标。此外,我们建议了一种新的措施,能够捕捉适应战略相对于监督培训的相对效力。我们核查了这些方法在自主驾驶环境实现多合成到现实路景基准的最新结果方面的有效性。