论文标题
实例自适应自我训练，用于无监督域的适应性
Instance Adaptive Self-Training for Unsupervised Domain Adaptation
论文作者
论文摘要
对于最近的深度学习模型，标记的培训数据与未标记的测试数据之间的差异是一个重大挑战。无监督的域适应（UDA）试图解决此类问题。最近的作品表明，自我训练是对UDA的强大方法。但是，现有方法在平衡可伸缩性和性能方面存在困难。在本文中，我们为UDA提出了一个实例自适应自我训练框架，以实现语义分割的任务。为了有效提高伪标签的质量，我们使用实例自适应选择器开发了一种新颖的伪标签生成策略。此外，我们提出了区域引导的正则化，以使伪标签区域平滑并锐化非伪标签区域。我们的方法是如此简洁有效，以至于很容易被推广到其他无监督的域适应方法。与最先进的方法相比，对“ GTA5至CityScapes”和“ Cityscapes to CityScapes”的实验表明了我们方法的出色表现。
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing scalability and performance. In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. Besides, we propose the region-guided regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. Our method is so concise and efficient that it is easy to be generalized to other unsupervised domain adaptation methods. Experiments on 'GTA5 to Cityscapes' and 'SYNTHIA to Cityscapes' demonstrate the superior performance of our approach compared with the state-of-the-art methods.
