Journal of Shanghai Jiao Tong University ›› 2021, Vol. 55 ›› Issue (9): 1158-1168.doi: 10.16183/j.cnki.jsjtu.2019.307

Special Issue: 《上海交通大学学报》2021年12期专题汇总专辑 《上海交通大学学报》2021年“自动化技术、计算机技术”专题

Previous Articles     Next Articles

A Domain Adaptive Semantic Segmentation Network Based on Improved Transformation Network

ZHANG Junning1, SU Qunxing2(), WANG Cheng3, XU Chao4, LI Yining5   

  1. 1. Army Engineering University, Shijiazhuang 050003, China
    2. Army Command College, Nanjing 210000, China
    3. Joint Operations Academy, National Defense University, Shijiazhuang 050003, China
    4. 32181 Troops, Xi’an 710032, China
    5. Research Institute of Chemical Defense, Academy of Military Sciences, Beijing 102205, China
  • Received:2019-10-23 Online:2021-09-28 Published:2021-10-08
  • Contact: SU Qunxing


Due to the high cost and time-consumption of artificial semantic tags, domain-based adaptive semantics segmentation is very necessary. For scenes with large gaps or pixels, it is easy to limit model training and reduce the accuracy of semantic segmentation. In this paper, a domain adaptive semantic segmentation network (DA-SSN) using the improved transformation network is proposed by eliminating the interference of large gap pictures and pixels through staged training and interpretable masks. First, in view of the problem of large domain gaps from some source graphs to target graphs and the difficulty in network model training, the training loss threshold is used to divide the source graph dataset with large gaps, and a phased transformation network training strategy is proposed. Based on the ensurance of the semantic alignment of small gap source images, the transformation quality of large gap source images is improved. In addition, in order to further reduce the gap between some pixels in the source image and the target image area, an interpretable mask is proposed. By predicting the gap between each pixel in the source image domain and the target image domain, the confidence is reduced, and the training loss of the corresponding pixel is ignored to eliminate the influence of large gap pixels on the semantic alignment of other pixels, so that model training only focuses on the domain gap of high-confidence pixels. The results show that the proposed algorithm has a higher segmentation accuracy than the original domain adaptive semantic segmentation network. Compared with the results of other popular algorithms, the proposed method obtains a higher quality semantic alignment, which shows the advantages of the proposed method with high accuracy.

Key words: computer vision, domain adaptive semantics segmentation, domain gap, semantic information integration, interpretable mask, staged training

CLC Number: