用轻量全局感知模块提升驾驶场景实时检测精度
DS MYOLO: A Reliable Object Detector Based on SSMs for Driving Scenarios
- 引入简化选择性扫描块捕获全局特征
- 在CCTSDB2021和VLD-45上实现高精度检测
- 适合资源受限的车载实时目标检测应用
准确的实时目标检测可提升高级驾驶辅助系统安全性，是驾驶场景中的关键组件。随着深度学习发展，基于CNN的YOLO实时检测器备受关注，但其局部感受野导致性能瓶颈。为突破限制，研究者引入基于Transformer的自注意力机制以获取全局感受野，但其二次复杂度带来巨大计算开销。近期，具有线性复杂度的Mamba通过全局选择性扫描取得显著进展。受此启发，我们提出新型检测器DS MYOLO：通过简化选择性扫描融合模块（SimVSS Block）捕捉全局特征信息，并有效整合网络深层特征；同时引入高效通道注意力卷积（ECAConv），增强跨通道特征交互，保持低计算复杂度。在CCTSDB 2021和VLD-45驾驶场景数据集上的大量实验表明，DS MYOLO在同等规模的YOLO系列实时检测器中展现出显著潜力与竞争优势。
原文摘要 · Abstract (English)
Accurate real-time object detection enhances the safety of advanced driver-assistance systems, making it an essential component in driving scenarios. With the rapid development of deep learning technology, CNN-based YOLO real-time object detectors have gained significant attention. However, the local focus of CNNs results in performance bottlenecks. To further enhance detector performance, researchers have introduced Transformer-based self-attention mechanisms to leverage global receptive fields, but their quadratic complexity incurs substantial computational costs. Recently, Mamba, with its linear complexity, has made significant progress through global selective scanning. Inspired by Mamba's outstanding performance, we propose a novel object detector: DS MYOLO. This detector captures global feature information through a simplified selective scanning fusion block (SimVSS Block) and effectively integrates the network's deep features. Additionally, we introduce an efficient channel attention convolution (ECAConv) that enhances cross-channel feature interaction while maintaining low computational complexity. Extensive experiments on the CCTSDB 2021 and VLD-45 driving scenarios datasets demonstrate that DS MYOLO exhibits significant potential and competitive advantage among similarly scaled YOLO series real-time object detectors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。