Mamba-UDA: Mamba Unsupervised Domain Adaptation for SAR Ship Detection

Existing SAR ship detectors perform well on data with consistent distributions but degrade significantly when faced with domain shifts and the absence of labeled data. Moreover, traditional CNNs struggle with global feature extraction due to the local receptive fields while transformer approaches struggle with computational efficiency when extracting global features from complex SAR images. Designing an effective cross-domain SAR ship detector that can handle unlabeled data with domain shifts remains a challenge. In this letter, we propose a novel Mamba-based unsupervised domain adaptation SAR ship detection model integrated with pseudo labels optimization strategy. First, we propose the Domain Adaptive State Space Model (DASSM) to construct the Mamba Mean Teacher framework for the first time, enhancing the capture of both global and local SAR image features at a linear time complexity and facilitating domain-invariant feature learning. To enhance the quality of pseudo labels, we design the Adaptive Pseudo Label Optimizer (APLO) module with Wise-IoU (WIoU) and dynamic dual-threshold pseudo label selector (DDPLS). The WIoU is utilized to improve the generation of pseudo labels, while DDPLS is further employed to categorize and optimize pseudo labels. Extensive experiments on public datasets illustrate the effectiveness and superiority of the proposed method for cross-domain detection of unlabeled SAR data.