Abstract:
Unsupervised domain adaptation (UDA) aims to improve model performance in the target domain by leveraging labeled data from the source domain while not requiring labeled ...Show MoreMetadata
Abstract:
Unsupervised domain adaptation (UDA) aims to improve model performance in the target domain by leveraging labeled data from the source domain while not requiring labeled data in the target domain. It has been widely applied in cross-domain semantic segmentation of remote sensing images (RSIs). Despite some advancements in this area, challenges such as class confusion due to color and texture similarities, class imbalance due to significant scale variations and sample imbalance continue to impede progress in UDA for RSI segmentation. To address these challenges, we propose a novel self-supervised teacher-student network framework, including two innovative techniques: mask-enhanced class mix (MECM) and scale-based rare class sampling (SRCS). The MECM method applies a high proportion of masks to mixed images derived from both source-domain images and target-domain images, which encourages the model to infer the semantic information of masked areas from the surrounding context, enhancing cross-domain contextual semantic learning and improving the recognition accuracy of similar classes. Additionally, SRCS increases the sampling proportion of small-scale rare classes, mitigating the issue of class imbalance. Experiments show that our method outperforms existing UDA techniques in terms of PA, mF1, and mIoU, achieving state-of-the-art results on three public datasets. Notably, in the Potsdam IRRG to Vaihingen UDA scenario, our method’s performance on the key metric, mIoU, even surpasses that of supervised training, demonstrating the superiority of our approach. Codes are available at https://github.com/Qiuyb-ai/UDA-With-ME-and-BS.
Published in: IEEE Transactions on Geoscience and Remote Sensing ( Volume: 63)
Funding Agency:

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
Xin Li (Senior Member, IEEE) received the Ph.D. degree from the State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China.
He is currently an Associate Professor with China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing image processing and artificial intelligence oceanography.
Xin Li (Senior Member, IEEE) received the Ph.D. degree from the State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China.
He is currently an Associate Professor with China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing image processing and artificial intelligence oceanography.View more

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
Yuanbo Qiu is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
His research interests include semantic segmentation and deep learning for remote sensing.
Yuanbo Qiu is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
His research interests include semantic segmentation and deep learning for remote sensing.View more

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
Jixiu Liao is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
Her research interests include visualization and visual analysis.
Jixiu Liao is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
Her research interests include visualization and visual analysis.View more

Institute of Future Technology, Nanjing University of Information Science and Technology, Nanjing, China
Fan Meng is currently an Assistant Professor with Nanjing University of Information Science and Technology, Nanjing, China. His research interests include AI4Science, especially in marine and meteorological applications.
Fan Meng is currently an Assistant Professor with Nanjing University of Information Science and Technology, Nanjing, China. His research interests include AI4Science, especially in marine and meteorological applications.View more

College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China
Peng Ren (Senior Member, IEEE) received the B.Eng. and M.Eng. degrees in electronic engineering from Harbin Institute of Technology, Harbin, China, and the Ph.D. degree in computer science from the University of York, York, U.K.
He is currently a Professor with the College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing and mac...Show More
Peng Ren (Senior Member, IEEE) received the B.Eng. and M.Eng. degrees in electronic engineering from Harbin Institute of Technology, Harbin, China, and the Ph.D. degree in computer science from the University of York, York, U.K.
He is currently a Professor with the College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing and mac...View more

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
Xin Li (Senior Member, IEEE) received the Ph.D. degree from the State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China.
He is currently an Associate Professor with China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing image processing and artificial intelligence oceanography.
Xin Li (Senior Member, IEEE) received the Ph.D. degree from the State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China.
He is currently an Associate Professor with China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing image processing and artificial intelligence oceanography.View more

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
Yuanbo Qiu is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
His research interests include semantic segmentation and deep learning for remote sensing.
Yuanbo Qiu is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
His research interests include semantic segmentation and deep learning for remote sensing.View more

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
Jixiu Liao is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
Her research interests include visualization and visual analysis.
Jixiu Liao is currently pursuing the master’s degree with China University of Petroleum (East China), Qingdao, China.
Her research interests include visualization and visual analysis.View more

Institute of Future Technology, Nanjing University of Information Science and Technology, Nanjing, China
Fan Meng is currently an Assistant Professor with Nanjing University of Information Science and Technology, Nanjing, China. His research interests include AI4Science, especially in marine and meteorological applications.
Fan Meng is currently an Assistant Professor with Nanjing University of Information Science and Technology, Nanjing, China. His research interests include AI4Science, especially in marine and meteorological applications.View more

College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China
Peng Ren (Senior Member, IEEE) received the B.Eng. and M.Eng. degrees in electronic engineering from Harbin Institute of Technology, Harbin, China, and the Ph.D. degree in computer science from the University of York, York, U.K.
He is currently a Professor with the College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing and machine learning.
Dr. Ren was a recipient of the K. M. Scott Prize from the University of York in 2011 and the Eduardo Caianiello Best Student Paper Award at the 18th International Conference on Image Analysis and Processing in 2015, as the co-author.
Peng Ren (Senior Member, IEEE) received the B.Eng. and M.Eng. degrees in electronic engineering from Harbin Institute of Technology, Harbin, China, and the Ph.D. degree in computer science from the University of York, York, U.K.
He is currently a Professor with the College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China. His research interests include remote sensing and machine learning.
Dr. Ren was a recipient of the K. M. Scott Prize from the University of York in 2011 and the Eduardo Caianiello Best Student Paper Award at the 18th International Conference on Image Analysis and Processing in 2015, as the co-author.View more