论文标题
合成数据可以改善遥感图像的对象检测结果吗？
Can Synthetic Data Improve Object Detection Results for Remote Sensing Images?
论文作者
论文摘要
深度学习方法需要足够的培训样本才能表现良好，但是要收集足够的真实培训数据并手动标记它们是一个挑战。在这封信中，我们建议使用具有广泛分布的现实合成数据，以提高遥感图像飞机检测的性能。具体而言，为了增加合成数据的可变性，我们在渲染过程中随机设置参数，例如实例的大小和背景图像类别。为了使综合图像更加逼真，然后使用Cyclegan使用Cycledan和实际未标记的图像来完善像素级别的合成图像。我们还用少量的真实数据微调模型，以获得更高的精度。在NWPU VHR-10，UCAS-AOD和DIOR数据集上进行的实验表明，该方法可用于增强实际数据不足。
Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide distribution to improve the performance of remote sensing image aircraft detection. Specifically, to increase the variability of synthetic data, we randomly set the parameters during rendering, such as the size of the instance and the class of background images. In order to make the synthetic images more realistic, we then refine the synthetic images at the pixel level using CycleGAN with real unlabeled images. We also fine-tune the model with a small amount of real data, to obtain a higher accuracy. Experiments on NWPU VHR-10, UCAS-AOD and DIOR datasets demonstrate that the proposed method can be applied for augmenting insufficient real data.
