{"ID":2838557,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17147","arxiv_id":"2511.17147","title":"A lightweight detector for real-time detection of remote sensing images","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.","short_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 i...","url_abs":"https://arxiv.org/abs/2511.17147","url_pdf":"https://arxiv.org/pdf/2511.17147v2","authors":"[\"Qianyi Wang\",\"Guoqiang Ren\"]","published":"2025-11-21T11:11:04Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false}