脉冲驱动的离散聚合用于事件相机目标检测
Spike-driven Discrete Aggregation for Event-based Object Detection
把事件流到稠密张量的表征聚合从「无差别累积」改成「阈值触发的离散选择」，用门控循环脉冲神经元实现可微的稀疏事件筛选，可直接替换事件检测/识别流水线中的事件体素化或时间聚合前端。
原文依据 adaptively and discretely selects informative events for differentiable aggregation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事件相机具有高动态范围与高时间分辨率，非常适合目标检测，尤其是在运动模糊和极端光照条件下。近期最优的事件相机目标检测工作主要关注骨干网络的高层设计。然而，构建有效的事件表征同样关键，因为它负责将异步事件流与检测网络所需的稠密张量连接起来。现有的大多数事件表征聚合策略在采样区间内持续累积所有事件而不做选择性过滤，不可避免地引入无信息事件，从而降低检测精度。为解决这一局限，我们引入一种新的视角，称为离散聚合，它自适应且离散地选择有信息的事件进行可微聚合。我们通过脉冲离散聚合（SDA）模块实现这一思路，该模块受脉冲神经网络（SNN）中基于阈值的脉冲发放机制启发，并使用门控循环脉冲神经元实现。此外，我们引入多时间尺度融合（MTF）方法，利用连续事件流中的粗粒度时序特征来进一步增强 SDA 的表征能力。在神经形态数据集上的实验结果表明，我们的方法在所有全脉冲架构中取得了最优性能，同时参数量更少，在 Gen1 上达到 43.4% mAP50:95（较先前工作提升 4.5%）。此外，我们的方法在噪声条件下表现出更优的鲁棒性，并与非脉冲模型具有良好的兼容性。
英文原文摘要 1665 字符
With their high dynamic range and temporal resolution, event cameras are well-suited for object detection, especially under motion blur and extreme illumination. Recent state-of-the-art works for event-based object detection primarily focus on the high-level design of backbones. However, developing effective event representations is equally crucial, as it bridges asynchronous event streams with the dense tensors required by detection networks. Most existing aggregation strategies for event representation continuously accumulate all events within sampled intervals without selective filtering, inevitably introducing uninformative events that degrade detection accuracy. To address this limitation, we introduce a novel perspective, termed Discrete Aggregation, which adaptively and discretely selects informative events for differentiable aggregation. We realize this through the Spiking Discrete Aggregation (SDA) module, which is inspired by the threshold-based spike firing mechanism in Spiking Neural Networks (SNNs) and implemented using gated recurrent spiking neurons. Additionally, we introduce the Multi-Timescale Fusion (MTF) method which leverages coarse-grained temporal features from continuous event streams to further enhance the representation capability of SDA. Experimental results on neuromorphic datasets demonstrate that our method achieves state-of-the-art performance among all fully spiking architectures while using fewer parameters, reaching 43.4% mAP\textsubscript 50:95 on Gen1 (+ 4.5% over prior art). Moreover, our method exhibits superior robustness under noisy conditions and shows strong compatibility with non-spiking models.