Self-Training based Unsupervised Domain Adaptation for Object Detection in Remote Sensing Imagery

We propose a novel two-stage Cross-Domain Self-Training (CDST) framework for unsupervised domain adaptive object detection in remote sensing. The first stage introduces the GAN-based domain transfer strategy to preliminarily mitigate the domain shift for higher-quality initial pseudo-labeled images, which utilizes the CycleGAN to transfer source domain images to match the target domain. Moreover, the key issue in tailoring the self-training to unsupervised domain adaptive detection lies in the quality of pseudo-labeled images. To select high-quality pseudo-labeled images under the domain shift circumstance, we propose hard example selection-based self-training with the three key steps: 1) Detector-based example division, which divides the detected examples into easy examples and hard ones according to their confidence level. 2) Confidence and relation joint score-based hard example selection, which combines two reliability levels calculated respectively by the detector and relation networks module to mine reliable examples. 3) Union example-based training image selection, which combines both easy and reliable hard examples to choose target domain images that may contain fewer detection errors. The experimental results on several remote sensing datasets demonstrate the effectiveness of our proposed framework. Compared with the baseline detector trained on the source dataset, our approach consistently improves the detection performance on the target dataset by 15.7%-16.8% mAP and achieves state-of-the-art results under various domain adaptation scenarios.