Scholarlink

<p>Although traditional object detection has advanced, accurate recognition of small objects remains challenging for conventional detectors under computational efficiency constraints. Specifically, small objects usually generate weak and sparse feature responses, which cause detectors to allocate attention to dominant regions. In such cases, YOLO-based detectors often suffer from imbalanced attention allocation, resulting in unsatisfactory detection accuracy. To address these challenges, a novel small object detector called Progressive Modular-Guided Network (PMG-Net) is proposed in this paper. PMG-Net includes three innovative plug-and-play modules: Feature Aggregation and Enhancement (FAE) module, Large Kernel Multiscale Fusion (LKMF) module, and Dynamic Dual Pooling Attention Convolution (DDPAC) module. First, the FAE module strengthens fine-grained features through dual-branch serial multi-dimensional attention. Second, the LKMF module is embedded in shallow layers. It captures small object context by enhancing representation through large kernel decomposition and multiscale fusion. Finally, the DDPAC module enhances local and global collaboration by adaptively adjusting attention regions with learnable parameters and balancing weight allocation across feature regions. Experiments show that, compared with the YOLOv11-N baseline, PMG-Net improves AP by 2.9% on VisDrone, 5.0% on VEDAI, 5.0% on GTSDB, 5.9% on TT100K, 1.4% on UAVDT, and 1.9% on RSOD, demonstrating its effectiveness under computational efficiency constraints. This design requires GPU-level parallelism for real-time processing of large-scale visual data.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PMG-Net: progressive modular-guided network for small object detection

  • 期刊论文

  • 发表日期：

    2026年3月17日

查看全文
  • Sichen Lin,
  • Xiaojie Li,
  • Li Xue,
  • Yuanshui Huang,
  • Huacong Chen,
  • Riqing Chen,
  • Lifang Wei,
  • Changcai Yang

摘要

Although traditional object detection has advanced, accurate recognition of small objects remains challenging for conventional detectors under computational efficiency constraints. Specifically, small objects usually generate weak and sparse feature responses, which cause detectors to allocate attention to dominant regions. In such cases, YOLO-based detectors often suffer from imbalanced attention allocation, resulting in unsatisfactory detection accuracy. To address these challenges, a novel small object detector called Progressive Modular-Guided Network (PMG-Net) is proposed in this paper. PMG-Net includes three innovative plug-and-play modules: Feature Aggregation and Enhancement (FAE) module, Large Kernel Multiscale Fusion (LKMF) module, and Dynamic Dual Pooling Attention Convolution (DDPAC) module. First, the FAE module strengthens fine-grained features through dual-branch serial multi-dimensional attention. Second, the LKMF module is embedded in shallow layers. It captures small object context by enhancing representation through large kernel decomposition and multiscale fusion. Finally, the DDPAC module enhances local and global collaboration by adaptively adjusting attention regions with learnable parameters and balancing weight allocation across feature regions. Experiments show that, compared with the YOLOv11-N baseline, PMG-Net improves AP by 2.9% on VisDrone, 5.0% on VEDAI, 5.0% on GTSDB, 5.9% on TT100K, 1.4% on UAVDT, and 1.9% on RSOD, demonstrating its effectiveness under computational efficiency constraints. This design requires GPU-level parallelism for real-time processing of large-scale visual data.