StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization

被引:43
|
作者
Tasar, Onur [1 ]
Tarabalka, Yuliya [2 ]
Giros, Alain [3 ]
Alliez, Pierre [1 ]
Clerc, Sebastien [4 ]
机构
[1] Univ Cote dAzur, INRIA, Valbonne, France
[2] LuxCarta, Valbonne, France
[3] Ctr Natl Etud Spatiales, Paris, France
[4] ACRI ST, Biot, France
关键词
NETWORKS;
D O I
10.1109/CVPRW50498.2020.00104
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 has recently been actively studied to increase the generalization capabilities of deep learning models. The vast majority of the domain adaptation methods tackle single-source case, where the model trained on a single source domain is adapted to a target domain. However, these methods have limited practical real world applications, since usually one has multiple source domains with different data distributions. In this work, we deal with the multi-source domain adaptation problem. Our method, namely StandardGAN, standardizes each source and target domains so that all the data have similar data distributions. We then use the standardized source domains to train a classifier and segment the standardized target domain. We conduct extensive experiments on two remote sensing data sets, in which the first one consists of multiple cities from a single country, and the other one contains multiple cities from different countries. Our experimental results show that the standardized data generated by StandardGAN allow the classifiers to generate significantly better segmentation.
引用
收藏
页码:747 / 756
页数:10
相关论文
共 50 条
  • [21] Multi-source domain adaptation of GPR data for IED detection
    Oturak, Mehmet
    Yuksel, Seniha Esen
    Kucuk, Sefa
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (05) : 1831 - 1839
  • [22] Multi-Source Domain Adaptation Using Ambient Sensor Data
    Dridi, Jawher
    Amayri, Manar
    Bouguila, Nizar
    APPLIED ARTIFICIAL INTELLIGENCE, 2024, 38 (01)
  • [23] Source Data-Free Unsupervised Domain Adaptation for Semantic Segmentation
    Ye, Mucong
    Zhang, Jing
    Ouyang, Jingpeng
    Yuan, Ding
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 2233 - 2242
  • [24] DEEP LEARNING FOR CROSS-DOMAIN BUILDING CHANGE DETECTION FROM MULTI-SOURCE VERY HIGH-RESOLUTION SATELLITE IMAGERY
    Gella, Getachew Workineh
    Lang, Stefan
    IGARSS 2024-2024 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, IGARSS 2024, 2024, : 421 - 426
  • [25] Transformer-Based Multi-Source Domain Adaptation Without Source Data
    Li, Gang
    Wu, Chao
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [26] Dual consistent pseudo label generation for multi-source domain adaptation without source data for medical image segmentation
    Cai, Binke
    Ma, Liyan
    Sun, Yan
    FRONTIERS IN NEUROSCIENCE, 2023, 17
  • [27] Multi-source domain adaptation of social media data for disaster management
    Khattar, Anuradha
    Quadri, S. M. K.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (06) : 9083 - 9111
  • [28] Multi-source domain adaptation of social media data for disaster management
    Anuradha Khattar
    S. M. K. Quadri
    Multimedia Tools and Applications, 2023, 82 : 9083 - 9111
  • [29] High-Resolution Rice Mapping Based on SNIC Segmentation and Multi-Source Remote Sensing Images
    Yang, Lingbo
    Wang, Limin
    Abubakar, Ghali Abdullahi
    Huang, Jingfeng
    REMOTE SENSING, 2021, 13 (06)
  • [30] Privacy-Preserving Multi-Source Domain Adaptation for Medical Data
    Han, Tianyi
    Gong, Xiaoli
    Feng, Fan
    Zhang, Jin
    Sun, Zhe
    Zhang, Yu
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (02) : 842 - 853