Fast Ship Detection in Remote Sensing Images Based on Multi-Attention Mechanism.

With the continuous development of deep learning in computer vision, object detection technology is constantly employed for processing remote sensing images. Especially, ship detection has become a significant and challenging task due to complex environmental factors (strong waves, clouds interference, etc.) and object issues (orientation, scale variety, density, etc.). Current detection methods pay more attention to the detection accuracy while ignoring the detection speed. In contrast with accuracy, detection speed is more important in some cases such as marine rescue and vessel tracking. Aiming at addressing these problems, we propose an enhanced YOLOv4(C-YOLOv4) which contains the feature fusion attention module (FAM) with a channel correlation loss(C-loss). C-loss is proposed to constrain the relations between object classes and channels while maintaining the intra-class and the inter-class separability. To evaluate the effectiveness of the proposed approach, comprehensive experiments are conducted on a public dataset HRSC2016. According to the experimental results, our proposed approach outperforms the baselines.