光谱成像技术研究室知识库

Cross-domain ship detection tries to identify synthetic aperture radar (SAR) ships by adapting knowledge from labeled optical images, without labor-intensive annotations. In practical applications, a few (e.g., one or three samples) labeled SAR samples are available, which provides additional supervision for SAR ships. However, the existing cross-domain methods ignore the SAR supervision (a few labeled and unlabeled SAR images), which limits their performances in a practical and under-investigated task: semisupervised cross-domain ship detection (SCSD). In this article, a dual-teacher framework is proposed to address the mutual interference between optical supervision and SAR supervision. First, both optical and SAR supervision are decomposed into two subtasks: cross-domain task and semisupervised task. Then, both cross-domain tasks and semisupervised tasks can be learned interactively in two individual teacher-student models. The teacher-student models generate pseudo-labels on unlabeled SAR images by a teacher network and fine-tune the student network. Finally, the dual-teacher framework retrains two teacher-student models in cotraining strategies. Both cross-domain datasets and semisupervised datasets are exploited to jointly improve the pseudo-label quality. The effectiveness of the dual-teacher framework has been fully experimentally demonstrated. The code is available at https://github.com/XiangtaoZheng/DualTeacher.