论文标题
PROCST：使用渐进式循环样式转移来增强语义细分
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
论文作者
论文摘要
使用合成数据来训练在现实世界数据上实现良好性能的神经网络是一项重要任务，因为它可以减少对昂贵数据注释的需求。但是，合成和现实世界数据具有域间隙。近年来，已经广泛研究了这种差距，也称为域的适应性。通过直接执行两者之间的适应性来缩小源（合成）和目标数据之间的域间隙是具有挑战性的。在这项工作中，我们提出了一个新颖的两阶段框架，用于改善图像数据上的域适应技术。在第一阶段，我们逐步训练一个多尺度神经网络，以从源域到目标域进行图像翻译。我们将新的转换数据表示为“目标中的源”（SIT）。然后，我们将生成的SIT数据插入任何标准UDA方法的输入。该新数据从所需的目标域缩小了域间隙，这有助于应用UDA进一步缩小差距的方法。我们通过与其他领先的UDA和图像到图像翻译技术进行比较来强调方法的有效性，当时用作SIT发电机。此外，我们通过三种用于语义细分的最先进的UDA方法（HRDA，daformer and proda）在两个UDA任务，GTA5到CityScapes和Synthia到CityScapes的三种最先进的语义分割方法，展示了我们的框架的改进。
Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it can reduce the need for costly data annotation. Yet, synthetic and real world data have a domain gap. Reducing this gap, also known as domain adaptation, has been widely studied in recent years. Closing the domain gap between the source (synthetic) and target (real) data by directly performing the adaptation between the two is challenging. In this work, we propose a novel two-stage framework for improving domain adaptation techniques on image data. In the first stage, we progressively train a multi-scale neural network to perform image translation from the source domain to the target domain. We denote the new transformed data as "Source in Target" (SiT). Then, we insert the generated SiT data as the input to any standard UDA approach. This new data has a reduced domain gap from the desired target domain, which facilitates the applied UDA approach to close the gap further. We emphasize the effectiveness of our method via a comparison to other leading UDA and image-to-image translation techniques when used as SiT generators. Moreover, we demonstrate the improvement of our framework with three state-of-the-art UDA methods for semantic segmentation, HRDA, DAFormer and ProDA, on two UDA tasks, GTA5 to Cityscapes and Synthia to Cityscapes.
