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
  • [41] A Multilevel-Guided Curriculum Domain Adaptation Approach to Semantic Segmentation for High-Resolution Remote Sensing Images
    Xi, Zhihao
    He, Xiangyu
    Meng, Yu
    Yue, Anzhi
    Chen, Jingbo
    Deng, Yupeng
    Chen, Jiansheng
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [42] Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images
    Collier, Edward
    Duffy, Kate
    Ganguly, Sangram
    Madanguit, Geri
    Kalia, Subodh
    Shreekant, Gayaka
    Nemani, Ramakrishna
    Michaelis, Andrew
    Li, Shuang
    Ganguly, Auroop
    Mukhopadhyay, Supratik
    2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2018, : 763 - 769
  • [43] DAugNet: Unsupervised, Multisource, Multitarget, and Life-Long Domain Adaptation for Semantic Segmentation of Satellite Images
    Tasar, Onur
    Giros, Alain
    Tarabalka, Yuliya
    Alliez, Pierre
    Clerc, Sebastien
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (02): : 1067 - 1081
  • [44] Segmentation method based on multiobjective optimization for very high spatial resolution satellite images
    Saleh El Joumani
    Salah Eddine Mechkouri
    Rachid Zennouhi
    Omar El Kadmiri
    Lhoussaine Masmoudi
    EURASIP Journal on Image and Video Processing, 2017
  • [45] Segmentation method based on multiobjective optimization for very high spatial resolution satellite images
    El Joumani, Saleh
    Mechkouri, Salah Eddine
    Zennouhi, Rachid
    El Kadmiri, Omar
    Masmoudi, Lhoussaine
    EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2017,
  • [46] Semantic Segmentation of Very-High-Resolution Remote Sensing Images via Deep Multi-Feature Learning
    Su, Yanzhou
    Cheng, Jian
    Bai, Haiwei
    Liu, Haijun
    He, Changtao
    REMOTE SENSING, 2022, 14 (03)
  • [47] STACKED ENCODER-DECODERS FOR ACCURATE SEMANTIC SEGMENTATION OF VERY HIGH RESOLUTION SATELLITE DATASETS
    Papadomanolaki, Maria
    Vakalopoulou, Maria
    Paragios, Nikos
    Karantzalos, Konstantinos
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 6927 - 6930
  • [48] High-resolution multi-source traffic data in New Zealand
    Li, Bo
    Yu, Ruotao
    Chen, Zijun
    Ding, Yingzhe
    Yang, Mingxia
    Li, Jinghua
    Wang, Jianxiao
    Zhong, Haiwang
    SCIENTIFIC DATA, 2024, 11 (01)
  • [49] DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images
    Cai, Yuxiang
    Yang, Yingchun
    Shang, Yongheng
    Shen, Zhengwei
    Yin, Jianwei
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [50] DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images
    Cai, Yuxiang
    Yang, Yingchun
    Shang, Yongheng
    Shen, Zhengwei
    Yin, Jianwei
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61