Combining Pixel-Level and Structure-Level Adaptation for Semantic Segmentation

被引:3
作者
Bi, Xiwen [1 ]
Chen, Dubing [1 ]
Huang, He [2 ]
Wang, Shidong [3 ]
Zhang, Haofeng [1 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China
[2] Nanjing Res Inst Elect Engn, Dept Data Link & Commun, Nanjing 210007, Peoples R China
[3] Newcastle Univ, Sch Engn, Newcastle Upon Tyne NE17RU, England
基金
中国国家自然科学基金;
关键词
Domain adaptation; Semantic segmentation; Category prototype; Consistency regularization;
D O I
10.1007/s11063-023-11220-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Domain adaptation for semantic segmentation requires pixel-level knowledge transfer from a labeled source domain to an unlabeled target domain. Existing approaches typically align the features of the source and target domains at different levels. However, they usually neglect the different adaptive complexities of different information flows within images. In this paper, we focus on combining two main information flows in semantic segmentation, ie., the pixel-level disparate information and image structure information. Specifically, we propose to combine two feature map-based prediction heads, which are thought to focus on pixel level and structure-level information, to accommodate different complexities by adjusting the attention to adaptation functions of the target domain. We then align the outputs from the two heads through a consistency regularization to realize informative complementarity. The combined prediction head further enables regularizing the distance between different pixel representations of different classes, thereby mitigating the mis-adaptation problem of similar classes. The proposed method can achieve more competitive results than current state-ofthe-art results on two publicly available benchmark datasets, ie., SYNTHIA -> Cityscapes and GTA5 -> Cityscapes.
引用
收藏
页码:9669 / 9684
页数:16
相关论文
共 64 条
  • [1] Progressive Feature Alignment for Unsupervised Domain Adaptation
    Chen, Chaoqi
    Xie, Weiping
    Huang, Wenbing
    Rong, Yu
    Ding, Xinghao
    Huang, Yue
    Xu, Tingyang
    Huang, Junzhou
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 627 - 636
  • [2] DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    Chen, Liang-Chieh
    Papandreou, George
    Kokkinos, Iasonas
    Murphy, Kevin
    Yuille, Alan L.
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) : 834 - 848
  • [3] Unsupervised Domain Adaptation via Discriminative Classes-Center Feature Learning in Adversarial Network
    Chen, Wendong
    Hu, Haifeng
    [J]. NEURAL PROCESSING LETTERS, 2020, 52 (01) : 467 - 483
  • [4] Semantic Image Segmentation with Feature Fusion Based on Laplacian Pyramid
    Chen, Yongsheng
    [J]. NEURAL PROCESSING LETTERS, 2022, 54 (05) : 4153 - 4170
  • [5] CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
    Chen, Yun-Chun
    Lin, Yen-Yu
    Yang, Ming-Hsuan
    Huang, Jia-Bin
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 1791 - 1800
  • [6] Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
    Choi, Jaehoon
    Kim, Taekyung
    Kim, Changick
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6829 - 6839
  • [7] The Cityscapes Dataset for Semantic Urban Scene Understanding
    Cordts, Marius
    Omran, Mohamed
    Ramos, Sebastian
    Rehfeld, Timo
    Enzweiler, Markus
    Benenson, Rodrigo
    Franke, Uwe
    Roth, Stefan
    Schiele, Bernt
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3213 - 3223
  • [8] Dundar Aysegul, 2018, ARXIV
  • [9] The PASCAL Visual Object Classes Challenge: A Retrospective
    Everingham, Mark
    Eslami, S. M. Ali
    Van Gool, Luc
    Williams, Christopher K. I.
    Winn, John
    Zisserman, Andrew
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 111 (01) : 98 - 136
  • [10] Dual Attention Network for Scene Segmentation
    Fu, Jun
    Liu, Jing
    Tian, Haijie
    Li, Yong
    Bao, Yongjun
    Fang, Zhiwei
    Lu, Hanqing
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 3141 - 3149