Dynamic Fusion Label Assignment Network for Remote Sensing Object Detection

doi:10.1109/TGRS.2025.3625573

Dynamic Fusion Label Assignment Network for Remote Sensing Object Detection

2025-01-01

0

PRE

AI

DOI：10.1109/TGRS.2025.3625573

Original

Original request for help

Save

Abstract

En 中文

Object detection in remote sensing images faces significant challenges posed by tiny objects, which are often overwhelmed by background noise. These tiny objects exhibit significant scale differences compared to larger objects, making it difficult to simultaneously consider both large and small objects during label assignment. In this article, a novel dynamic fusion label assignment network (DFLAN) is proposed to address these problems. First, to effectively extract features of tiny objects in background noise, we introduce a novel feature selection interactive pyramid network. Second, a novel dynamic fusion label assignment (DFLA) algorithm is developed, which achieves a collaborative approach to label assignment for both tiny and large objects. Finally, a new decoupling detection head is proposed to prevent task coupling from interfering with the already weak features of tiny objects. The proposed DFLAN method achieves state-of-the-art performance on two widely used datasets: DOTA-v1.0 (79.42% mAP), HRSC2016 (98.86% mAP), and DIOR-R (67.68% mAP).

Keywords:

Feature fusion

label assignment

oriented object detection

task decoupling

Vision Mamba

Dynamic Fusion Label Assignment Network for Remote Sensing Object Detection

Abstract

Journal

Organization