Enhancing the detection capabilities of marine vessels is crucial for maritime security and intelligence acquisition. However, accurately identifying small ships in complex oceanic environments remains a significant challenge, as these targets are frequently obscured by ocean waves and other disturbances, compromising recognition accuracy and stability. To address this issue, we propose YOLO-ssboat, a novel small-target ship recognition algorithm based on the YOLOv8 framework. YOLO-ssboat integrates the C2f_DCNv3 module to extract fine-grained features of small vessels while mitigating background interference and preserving critical target details. Additionally, it employs a high-resolution feature layer and incorporates a Multi-Scale Weighted Pyramid Network (MSWPN) to enhance feature diversity. The algorithm further leverages an improved multi-attention detection head, Dyhead_v3, to refine the representation of small-target features. To tackle the challenge of wake waves from moving ships obscuring small targets, we introduce a gradient flow mechanism that improves detection efficiency under dynamic conditions. The Tail Wave Detection Method synergistically integrates gradient computation with target detection techniques. Furthermore, adversarial training enhances the network’s robustness and ensures greater stability. Experimental evaluations on the Ship_detection and Vessel datasets demonstrate that YOLO-ssboat outperforms state-of-the-art detection algorithms in both accuracy and stability. Notably, the gradient flow mechanism enriches target feature extraction for moving vessels, thereby improving detection accuracy in wake-disturbed scenarios, while adversarial training further fortifies model resilience. These advancements offer significant implications for the long-range monitoring and detection of maritime vessels, contributing to enhanced situational awareness in expansive oceanic environments.

Transformers have performed favorably in recent hyperspectral unmixing studies in which the self-attention mechanism possesses the ability to retain spectral information and spatial details. However, the lack of reliable prior information for correction guidance has resulted in an inadequate accuracy and robustness of the network. To benefit from the advantages of the Transformer architecture and to improve the interpretability and robustness of the network, a dual-branch network with prior information correction, incorporating a Transformer network (PICT-Net), is proposed. The upper branch utilizes pre-extracted endmembers to provide pure pixel prior information. The lower branch employs a Transformer structure for feature extraction and unmixing processing. A weight-sharing strategy is employed between the two branches to facilitate information sharing. The deep integration of prior knowledge into the Transformer architecture effectively reduces endmember variability in hyperspectral unmixing and enhances the model’s generalization capability and accuracy across diverse scenarios. Experimental results from experiments conducted on four real datasets demonstrate the effectiveness and superiority of the proposed model.