论文标题
域适应的一致性正则化
Consistency Regularization for Domain Adaptation
论文作者
论文摘要
培训语义细分模型的现实世界注释收集是一个昂贵的过程。无监督的域适应性（UDA）试图通过研究如何使用更多可访问的数据（例如合成数据）来训练和适应现实世界图像的情况，而无需其注释。最近的UDA方法通过使用学生和教师网络对像素的分类损失进行培训，适用于自学习。在本文中，我们建议通过对网络输出中元素之间的像素间关系进行建模，将一致性正则项添加到半监督UDA中。我们通过将其应用于最先进的deformer框架上，并将GTA5上的MIOU1绩效应用于CityScapes基准，并将MIOU16在Synthia上的MIOU16在Synthia上提高MIOU19的性能，从而证明了拟议的一致性正规化项的有效性，并将MIOU1的性能提高到CityScapes Benchmark，并将MIOU16的MIOU1绩效提高到CityScapes基准。
Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic data can be used to train and adapt models to real world images without requiring their annotations. Recent UDA methods applies self-learning by training on pixel-wise classification loss using a student and teacher network. In this paper, we propose the addition of a consistency regularization term to semi-supervised UDA by modelling the inter-pixel relationship between elements in networks' output. We demonstrate the effectiveness of the proposed consistency regularization term by applying it to the state-of-the-art DAFormer framework and improving mIoU19 performance on the GTA5 to Cityscapes benchmark by 0.8 and mIou16 performance on the SYNTHIA to Cityscapes benchmark by 1.2.
