Spe-BEVHead：重新审视鸟瞰图目标检测的检测头设计
Spe-BEVHead: Rethinking the Detection Head Design for Bird's-Eye-View Object Detection
针对 BEV 检测头这一被忽视的环节，提出几何对齐的旋转框分类核与局部响应精炼模块，可直接替换现有 BEV 主干上的 center-based 检测头，在无 NMS 的端到端设定下取得增益，对做 BEV 3D 检测的读者是一个即插即用的改进点。
原文依据 a Rotated Box Kernel that generates geometry-aligned classification weights
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论鸟瞰图（BEV）检测凭借强大的感知能力，已成为自动驾驶中 3D 目标检测的主流范式。然而，现有方法大多聚焦于构建高质量的 BEV 特征表示，却忽视了任务特定检测头的设计。实践中，它们直接沿用最初为 2D 检测开发的基于中心的检测头，未做任何针对性优化。这带来了三个固有局限：(i) 用于分类的高斯核与真实 BEV 目标之间存在几何失配；(ii) 在无 NMS 的情况下端到端性能下降；(iii) 监督信号稀疏。为解决这些问题，我们提出 Spe-BEVHead，一种专为 BEV 3D 目标检测定制的检测头。Spe-BEVHead 引入三项面向 BEV 的适配：(1) 旋转框核，用于生成几何对齐的分类权重；(2) 局部响应精炼模块（LRRM），用于抑制非峰值响应并提升端到端性能；(3) 双分支架构，提供更丰富的监督信号以促进更稳健的学习，同时天然保持端到端推理的性能。大量实验表明，Spe-BEVHead 可无缝集成到现有 BEV 主干中，带来直接的性能提升，并在具有挑战性的端到端设定下保持有竞争力的性能。
英文原文摘要 1470 字符
Bird's-Eye-View (BEV) detection has become a dominant paradigm for 3D object detection in autonomous driving, due to its strong perception capability. However, most existing methods mainly focus on constructing high-quality BEV feature representations, while neglecting the design of task-specific detection heads. In practice, they directly adopt the center-based head originally developed for 2D detection, without any specific optimization. This leads to three inherent limitations: (i) a geometric mismatch between the Gaussian kernel used for classification and the real BEV object, (ii) degraded end-to-end performance without Non-Maximum Suppression (NMS), and (iii) sparse supervisory signals. To address these issues, we propose Spe-BEVHead, a detection head specifically tailored for BEV 3D object detection. Spe-BEVHead introduces three BEV-specific adaptations: (1) a Rotated Box Kernel that generates geometry-aligned classification weights, (2) a Local Response Refinement Module (LRRM) that suppresses non-peak responses and improves end-to-end performance, and (3) a dual-branch architecture that provides richer supervisory signals to promote more robust learning while inherently preserving the performance for end-to-end inference. Extensive experiments show that Spe-BEVHead can be seamlessly integrated into existing BEV backbones, delivering direct performance gains while retaining competitive performance under the challenging end-to-end setting.