基于改进YOLO11s的跨模态学习红外目标检测方法OA

Addressing the core challenge of model severely degraded detection accuracy in infrared object detection due to scarce training data and insufficient annotations,this paper proposes a cross-modal learning-based infrared target detection method based on an improved YOLO11s.The method mitigates the challenge of scarce infrared data by leveraging the abundance of visible-light data.Specifically,it incorporates:A combination of diverse data augmentation strategies to simu-late the infrared domain distribution;A lightweight module that reduces model complexity and op-timizes deployment on resource-constrained edge devices;Integration of a partial self-attention mechanism after the C2 PSA module to optimize visible-light feature representation,thereby im-proving the mode'l s cross-modal generalization capability for the infrared domain.Experimental results demonstrate that the proposed method achieves the mAP of 52.2％,while maintaining a parame-ter count of 8.8×106 on the Drone Vehicle dataset.Compared to existing mainstream object detection al-gorithms,it exhibits significant advantages in both model lightweight and detection accuracy,providing an efficient solution for infrared target detection under scarce data scenarios.