提出自适应融合与密度路由专家，提升人群计数精度。
DCA-MoE: Spatially Adaptive Cross-Layer Fusion and Density-Routed Experts for Crowd Counting
- 按位置自适应融合多层特征，动态调整权重。
- 基于密度分配不同感受野专家，提升局部精度。
- 适用于复杂场景下人群密度估计，适合计算机视觉研究者。
人群计数需在视角变化、头像大小差异、遮挡和背景杂乱等复杂条件下准确恢复局部密度。尽管现代计数目标提供强空间监督，但许多多级解码器仍采用空间不变的特征融合，并对所有位置使用统一感受野。本文提出DCA-MoE框架，结合空间自适应层融合（SALF）与密度路由多感受野专家（DR-MoE）。SALF在四个对齐的主干特征上预测位置相关的权重；DR-MoE为每个位置分配局部、中程和大范围残差专家的软混合。采用类EBC的头部重建块密度，结合DMCount监督与辅助路由平衡项训练解码器，不更新主干。在NWPU-Crowd验证集上，基于DINOv3 ViT-L/16的最强配置达31.7 MAE和72.2 RMSE；ViT-B/16完整模型为32.2/75.9。跨数据集结果仍不一致，部分基线报告单种子独立选取的最小值。证据支持空间自适应融合与路由的可行性，但更广泛的成对与多种子评估仍有待开展以实现因果归因。
原文摘要 · Abstract (English)
Crowd counting must recover reliable local density under severe variations in perspective, head scale, occlusion, and background clutter. Although modern counting objectives provide strong spatial supervision, many multi-level decoders still use spatially invariant feature fusion and apply one receptive-field pattern to every location. We propose DCA-MoE, a framework that makes both decisions content dependent while retaining a frozen DINOv3 encoder. Spatially Adaptive Layer Fusion (SALF) predicts position-wise weights over four aligned backbone features, and Density-Routed Multi-Receptive-Field Experts (DR-MoE) assigns each location a soft mixture of local, mid-range, and large-context residual experts. An EBC-style head reconstructs block density, while DMCount supervision and an auxiliary routing-balance term train the decoder without updating the backbone. On the NWPU-Crowd validation split, the strongest paired configuration, based on DINOv3 ViT-L/16, obtains 31.7 MAE and 72.2 RMSE; the matched ViT-B/16 full model obtains a paired 32.2/75.9. Cross-dataset results remain mixed, and several component baselines currently report independently selected minima from a single seed. The evidence therefore supports the feasibility of spatially adaptive fusion and routing, while broader paired and multi-seed evaluation remains necessary for causal attribution.
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。