A lightweight detector for real-time detection of remote sensing images

TL;DR

This paper introduces DMG-YOLO, a lightweight real-time detector optimized for small object detection in remote sensing images, combining novel feature extraction and fusion modules for improved accuracy and efficiency.

Contribution

The paper presents a novel dual-branch feature extraction module and a multi-scale feature fusion approach tailored for small object detection in remote sensing imagery.

Findings

Achieves competitive mAP on VisDrone2019 and NWPU VHR-10 datasets.

Maintains a lightweight model size suitable for real-time applications.

Enhances small object detection accuracy through global-local feature fusion.

Abstract

Remote sensing imagery is widely used across various fields, yet real-time detection remains challenging due to the prevalence of small objects and the need to balance accuracy with efficiency. To address this, we propose DMG-YOLO, a lightweight real-time detector tailored for small object detection in remote sensing images. Specifically, we design a Dual-branch Feature Extraction (DFE) module in the backbone, which partitions feature maps into two parallel branches: one extracts local features via depthwise separable convolutions, and the other captures global context using a vision transformer with a gating mechanism. Additionally, a Multi-scale Feature Fusion (MFF) module with dilated convolutions enhances multi-scale integration while preserving fine details. In the neck, we introduce the Global and Local Aggregate Feature Pyramid Network (GLAFPN) to further boost small object detection through global-local feature fusion. Extensive experiments on the VisDrone2019 and NWPU VHR-10 datasets show that DMG-YOLO achieves competitive performance in terms of mAP, model size, and other key metrics.