发表机构
University of California, Los Angeles (UCLA)（加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出轮廓引导的频谱路由方法，通过有序融合空间、频谱和边界信息，并采用小波子带训练增强，在CityPersons上实现实时行人检测性能提升。
AI 中文摘要
驾驶场景中的实时行人检测受到三种相互耦合的失效模式的制约：小目标丢失判别性证据，遮挡削弱几何支持，天气或光照变化扭曲外观统计。我们通过统一的“轮廓引导的频谱路由”视角来构建检测器，而不是将频率处理、注意力和边界推理视为独立的附加组件。该检测器按规定的顺序路由信息：首先用全局频谱上下文增强空间证据，然后深度表示交换空间和频谱线索，最后跨尺度融合以边界-语义不一致为条件。这种排序产生了一个紧凑的表示流水线，其中低频上下文稳定全局结构，而高频证据保护小目标轮廓。我们进一步保留了一种小波子带训练变换，该变换独立扰动低频和高频系数，针对雾、雨、雪和低光照引起的外观变化。该公式在每个阶段暴露一个单一的路由变量，并区分可重用的信号变换与决定每个信号注入位置的任务特定策略。在CityPersons上，所提出的检测器获得70.4 AP$_{50}$和44.2 AP$_{50:95}$，而RT-DETR为68.1和42.2，而完整的小波增强配置达到71.1和44.6。
英文摘要
Real-time pedestrian detection in driving scenes is constrained by three coupled failure modes: tiny targets lose discriminative evidence, occlusion weakens geometric support, and weather or illumination changes distort appearance statistics. We formulate the detector through a unified \emph{contour-guided spectral routing} view rather than treating frequency processing, attention, and boundary reasoning as independent add-ons. The detector routes information in a prescribed order: spatial evidence is first augmented with global spectral context, deep representations then exchange spatial and spectral cues, and cross-scale fusion is finally conditioned on boundary--semantic disagreement. This ordering yields a compact representation pipeline in which low-frequency context stabilizes global structure while high-frequency evidence protects small-object contours. We further retain a wavelet-subband training transformation that perturbs low- and high-frequency coefficients independently, targeting appearance shifts caused by fog, rain, snow, and low illumination. The formulation exposes a single routing variable at each stage and distinguishes reusable signal transforms from the task-specific policy that decides where each signal is injected. On CityPersons, the proposed detector obtains 70.4 AP$_{50}$ and 44.2 AP$_{50:95}$, compared with 68.1 and 42.2 for RT-DETR, while the full wavelet-augmented configuration reaches 71.1 and 44.6.
