Scholarlink

<p>Tiny object detection is a critical challenge in computer vision with significant applications in aerial surveillance and emergency response systems. Existing methods suffer from three persistent limitations: indistinct feature representations for small-scale targets, severe background interference, and structural detail degradation during multi-scale processing. To address these issues, we propose MST-DETR, a multi-module collaborative framework with three key innovations. First, the Adaptive Multi-Scale Saliency Enhancement (AMSE) module dynamically adjusts feature fusion weights through spatial attention, enhancing discriminative object characteristics while maintaining computational efficiency. Second, the Efficient Upsampling Feature Reorganization Module (EUFRM) improves feature alignment via progressive upsampling and optimized channel interactions, boosting classification robustness in complex environments. Third, the Dynamic Partial Downsampling (DPD) module integrates deformable operations with wavelet-based processing to minimize structural information loss during feature extraction. Extensive experimental results demonstrate that MST-DETR achieves a 2.5%–7.2% improvement in <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(mAP_{50}^{val}\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>m</mi> <mi>A</mi> <msubsup> <mi>P</mi> <mrow> <mn>50</mn> </mrow> <mrow> <mi mathvariant="italic">val</mi> </mrow> </msubsup> </mrow> </math></EquationSource> </InlineEquation> compared with RT-DETR-R18 on the SIMD and VisDrone2019 datasets. Meanwhile, it significantly reduces false positives and missed detections, further validating the effectiveness and robustness of the proposed method in tiny object detection tasks.</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

MST-DETR: A multi-scale enhanced tiny object detection framework

  • 期刊论文

  • 发表日期：

    2026年1月14日

查看全文
  • Lingling Li,
  • Zonghao Zhu,
  • Xuezhuan Zhao,
  • Xiaoyan Shao,
  • Shiqin Diao,
  • Yang Mei

摘要

Tiny object detection is a critical challenge in computer vision with significant applications in aerial surveillance and emergency response systems. Existing methods suffer from three persistent limitations: indistinct feature representations for small-scale targets, severe background interference, and structural detail degradation during multi-scale processing. To address these issues, we propose MST-DETR, a multi-module collaborative framework with three key innovations. First, the Adaptive Multi-Scale Saliency Enhancement (AMSE) module dynamically adjusts feature fusion weights through spatial attention, enhancing discriminative object characteristics while maintaining computational efficiency. Second, the Efficient Upsampling Feature Reorganization Module (EUFRM) improves feature alignment via progressive upsampling and optimized channel interactions, boosting classification robustness in complex environments. Third, the Dynamic Partial Downsampling (DPD) module integrates deformable operations with wavelet-based processing to minimize structural information loss during feature extraction. Extensive experimental results demonstrate that MST-DETR achieves a 2.5%–7.2% improvement in \(mAP_{50}^{val}\) m A P 50 val compared with RT-DETR-R18 on the SIMD and VisDrone2019 datasets. Meanwhile, it significantly reduces false positives and missed detections, further validating the effectiveness and robustness of the proposed method in tiny object detection tasks.