What type of study is this?

This is a Experimental Study study.

October 11, 2025Open Access

YOLO-PFA: Advanced Multi-Scale Feature Fusion and Dynamic Alignment for SAR Ship Detection

Key Points

YOLO-PFA achieves an mAP@0.5 of 95%, improving detection performance significantly compared to previous models.
The integration of a bidirectional feature pyramid network enhances cross-scale feature fusion, crucial for detecting variable target sizes.
C2f-Partial Feature Aggregation optimizes the efficiency of feature extraction, ensuring better performance on complex objects.
Dynamic alignment in the detection head optimizes interaction between classification and regression features for improved accuracy.

Abstract

Maritime ship detection faces challenges due to complex object poses, variable target scales, and background interference. This paper introduces YOLO-PFA, a novel SAR ship detection model that integrates multi-scale feature fusion and dynamic alignment. By leveraging the Bidirectional Feature Pyramid Network (BiFPN), YOLO-PFA enhances cross-scale weighted feature fusion, improving detection of objects of varying sizes. The C2f-Partial Feature Aggregation (C2f-PFA) module aggregates raw and processed features, enhancing feature extraction efficiency. Furthermore, the Dynamic Alignment Detection Head (DADH) optimizes classification and regression feature interaction, enabling dynamic collaboration. Experimental results on the iVision-MRSSD dataset demonstrate YOLO-PFA’s superiority, achieving an mAP@0.5 of 95%, outperforming YOLOv11 by 1.2% and YOLOv12 by 2.8%. This paper contributes significantly to automated maritime target detection.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper