发表机构
The University of Suwon（水原大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对轻量级人脸检测中局部融合难以建模全局跨尺度依赖的问题，提出Weave Mamba Fusion，通过逐列交错金字塔尺度实现高效跨尺度交互，集成后以0.34M参数在WIDER FACE上达到91.41%平均精度。
AI 中文摘要
特征金字塔方法（从FPN到BiFPN）通过融合多尺度特征在人脸检测中取得了强劲性能。然而，在无约束条件下（如小尺度、遮挡和极端姿态）检测人脸仍然困难，因为这需要局部融合无法建模的全局跨尺度依赖。状态空间模型（如Mamba）通过将特征扫描为序列，以线性复杂度提供全局上下文，因此为该问题提供了有前景的方向。然而，这种扫描需要将两个金字塔尺度合并为单个特征图，而合并方式决定了跨尺度结构是否得以保留。求和（Summation）在扫描前将两个尺度折叠，导致扫描无可利用的跨尺度结构；而拼接（Concatenation）虽保留两个尺度，但代价高得多。为解决此问题，我们提出Weave Mamba Fusion（WMF），它将两个相邻金字塔尺度逐列交错，使得水平双向SS2D扫描的每一步都从一个尺度移动到另一个尺度。通过部分通道处理和免参数解交织，WMF在保留特征结构的同时实现了高效的跨尺度交互。将WMF集成到每个融合节点中，得到WeaveBiFPN，即我们WeaveFace检测器的颈部。在WIDER FACE上，WeaveFace仅用0.34M参数和1.16 GFLOPs就达到91.41%的平均精度（mean AP），优于此前0.5M参数以下的检测器。其最大增益出现在Hard子集上，达到87.14%的AP。代码已公开，见URL。
英文摘要
Feature pyramid methods, from FPN to BiFPN, have achieved strong performance in face detection by fusing multi-scale features. However, detecting faces under unconstrained conditions, such as small scale, occlusion, and extreme pose, remains difficult, as it requires global cross-scale dependencies that local fusion cannot model. State space models such as Mamba provide global context with linear complexity by scanning features as a sequence, and therefore offer a promising direction for this problem. Nevertheless, such a scan needs the two pyramid scales combined into a single feature map, and the way they are combined determines whether cross-scale structure is preserved. Summation collapses the two scales before the scan, so the scan has no cross-scale structure to exploit, while concatenation keeps both scales but at far higher cost. To address this, we propose \textbf{Weave Mamba Fusion (WMF)}, which interleaves two adjacent pyramid scales column by column so that each step of a horizontal bidirectional SS2D scan moves from one scale to the other. With partial-channel processing and parameter-free de-weaving, WMF enables efficient cross-scale interaction while preserving feature structure. Integrating WMF into every fusion node yields \textbf{WeaveBiFPN}, the neck of our \textbf{WeaveFace} detector. On WIDER FACE, WeaveFace achieves 91.41\% mean AP with only 0.34M parameters and 1.16 GFLOPs, outperforming prior detectors under 0.5M parameters. Its largest gains are on the Hard subset, where it reaches 87.14\% AP. The code is publicly available at \url{https://github.com/dohun-mat/WeaveMambaFusion}.
