C³DA: A Universal Domain Adaptation Method for Scene Classification From Remote Sensing Imagery

Jiaxu Guo, Yushan Lai, Jinxiao Zhang, Juepeng Zheng, Haohuan Fu, Lin Gan, Liang Hu, Gaochao Xu, Xilong Che

Abstract: Various remote sensing applications have widely used domain adaptation (DA) methods. Since it does not need to add human interpretation in the target domain, it can be used in cross-region, multitemporal, and multisensor application scenarios. In order to further optimize the design of the loss function and better address the challenges of DA in remote sensing, in this letter, we propose a new universal DA method named C3DA for scene recognition of remote sensing images. It has a comprehensive C3 criterion for recognizing the “unknown” classes by innovatively fusing confidence, consistency, and certainty of samples to make our network training more efficient. We evaluate the performance of our proposed method based on six transfer tasks on three remote sensing datasets. The evaluation results show that our proposed method achieves an average H-score of 58.44%, significantly higher than other SOTA universal DA methods with an average improvement of 2.32%~29.43%. Compared to the baseline ResNet-50, it achieves up to 19.92% improvement, demonstrating that the proposed method outperforms the universal DA scenario. In the future, we also plan to expand the application of this method to more scenarios.