Guo Dazhou, Pei Yanting, Zheng Kang, Yu Hongkai, Lu Yuhang, Wang Song
IEEE Trans Image Process. 2019 Aug 26. doi: 10.1109/TIP.2019.2936111.
Degraded image semantic segmentation is of great importance in autonomous driving, highway navigation systems, and many other safety-related applications and it was not systematically studied before. In general, image degradations increase the difficulty of semantic segmentation, usually leading to decreased semantic segmentation accuracy. Therefore, performance on the underlying clean images can be treated as an upper bound of degraded image semantic segmentation. While the use of supervised deep learning has substantially improved the state of the art of semantic image segmentation, the gap between the feature distribution learned using the clean images and the feature distribution learned using the degraded images poses a major obstacle in improving the degraded image semantic segmentation performance. The conventional strategies for reducing the gap include: 1) Adding image-restoration based pre-processing modules; 2) Using both clean and the degraded images for training; 3) Fine-tuning the network pre-trained on the clean image. In this paper, we propose a novel Dense-Gram Network to more effectively reduce the gap than the conventional strategies and segment degraded images. Extensive experiments demonstrate that the proposed Dense-Gram Network yields stateof-the-art semantic segmentation performance on degraded images synthesized using PASCAL VOC 2012, SUNRGBD, CamVid, and CityScapes datasets.
退化图像语义分割在自动驾驶、公路导航系统以及许多其他与安全相关的应用中具有重要意义，且此前尚未得到系统研究。一般来说，图像退化会增加语义分割的难度，通常会导致语义分割准确率下降。因此，基础干净图像上的性能可被视为退化图像语义分割的上限。虽然监督深度学习的应用显著提升了语义图像分割的技术水平，但使用干净图像学习到的特征分布与使用退化图像学习到的特征分布之间的差距，成为了提高退化图像语义分割性能的主要障碍。减少这种差距的传统策略包括：1）添加基于图像恢复的预处理模块；2）使用干净图像和退化图像进行训练；3）对在干净图像上预训练的网络进行微调。在本文中，我们提出了一种新颖的密集Gram网络，以比传统策略更有效地减少差距并分割退化图像。大量实验表明，所提出的密集Gram网络在使用PASCAL VOC 2012、SUNRGBD、CamVid和CityScapes数据集合成的退化图像上产生了领先的语义分割性能。
