用于事件行人重识别的频谱引导特征增强网络
Spectrum-guided Feature Enhancement Network for Event Person Re-Identification
AI总结：
针对事件流噪声大且语义稀疏导致行人重识别困难的问题，提出SFE-Net网络，通过多粒度频谱注意力机制和连续补丁丢弃模块有效过滤噪声并捕获鲁棒行人特征，实现最佳性能。
摘要：
作为前沿的生物传感器，事件相机在计算机视觉领域具有巨大潜力，尤其在隐私保护方面。然而，与传统相机相比，事件流通常包含噪声且语义极其稀疏，给基于事件的行人重识别（event Re-ID）带来了巨大挑战。为此，我们提出了一种新的事件行人重识别网络：Spectrum-guided Feature Enhancement Network（SFE-Net，频谱引导特征增强网络）。该网络包含两个创新组件：Multi-grain Spectrum Attention Mechanism（MSAM，多粒度频谱注意力机制）和Consecutive Patch Dropout Module（CPDM，连续补丁丢弃模块）。MSAM采用傅里叶频谱变换策略过滤事件噪声，同时利用事件引导的多粒度注意力策略增强并捕获具有判别性的行人语义。CPDM采用连续补丁丢弃策略生成多个不完整的特征图，促使深度Re-ID模型同等感知人体每个有效区域，从而捕获鲁棒的行人描述符。在多个Event Re-ID数据集上的大量实验表明，我们的SFE-Net在此任务中取得了最佳性能。
英文摘要：
As a cutting-edge biosensor, the event camera holds significant potential in the field of computer vision, particularly regarding privacy preservation. However, compared to traditional cameras, event streams often contain noise and possess extremely sparse semantics, posing a formidable challenge for event-based person re-identification (event Re-ID). To address this, we introduce a novel event person re-identification network: the Spectrum-guided Feature Enhancement Network (SFE-Net). This network consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM). MSAM employs a fourier spectrum transform strategy to filter event noise, while also utilizing an event-guided multi-granularity attention strategy to enhance and capture discriminative person semantics. CPDM employs a consecutive patch dropout strategy to generate multiple incomplete feature maps, encouraging the deep Re-ID model to equally perceive each effective region of the person's body and capture robust person descriptors. Extensive experiments on Event Re-ID datasets demonstrate that our SFE-Net achieves the best performance in this task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
