Abstract: Since the FCN network was proposed in 2014, a series of deep learning architectures for image semantic segmentation such as SegNet and DeepLab have been proposed. Compared with the traditional methods, these architectures are better and faster, and can be applied to the segmentation of natural images. This paper focuses on the image semantic segmentation technology. The commonly used data sets and typical network architectures are analyzed. And a comprehensive study is conducted about the new progress since 2017. The current evaluation indicators are used to compare and analyze the semantic segmentation effects of the main models. Finally, the challenges faced by semantic segmentation technology and the possible development trends are prospected.

Key words: deep learning, image segmentation, semantic segmentation

摘要： 自FCN网络在2014年提出后，SegNet、DeepLab等一系列关于图像语义分割的深度学习架构被相继提出。与传统方法相比，这些架构效果更好、运算速度更快，已经能够运用于自然图像的分割处理。围绕图像语义分割技术，对常用的数据集和典型网络架构进行了梳理分析，对2017年以来的新进展进行了综合研究，利用主流评价指标对主要模型的语义分割效果进行了比较和分析。对语义分割技术面临的挑战以及可能的发展趋势进行了展望。

关键词: 深度学习, 图像分割, 语义分割