SpikeTrack：基于脉冲神经网络的高性能节能事件相机目标跟踪
SpikeTrack: High-performance and Energy-efficient Event-Based Object Tracking with Spiking Neural Network
把纯脉冲驱动的 SNN 骨干与 DI-LIF 自适应整数激活结合，用于事件相机单目标跟踪；其 MSST 训练范式（多搜索序列配单模板）可作为事件数据上时序依赖建模与低功耗推理的可复用方案。
原文依据 a purely spike-driven framework for single-object tracking that addresses the shortcomings of RGB-based approaches in fast-motion or target appearance change
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凭借微秒级时序分辨率与宽动态范围，在目标跟踪领域受到广泛关注，然而在该领域有效利用脉冲神经网络（SNN）仍具挑战。本文提出 SpikeTrack，一个纯脉冲驱动的单目标跟踪框架，用以解决基于 RGB 的方法在快速运动或目标外观变化情形下的不足。SpikeTrack 的核心是多搜索序列与单模板（MSST）训练范式，该范式能够捕获丰富的时序依赖；同时引入动态整数泄漏积分发放（DI-LIF）神经元，在训练阶段根据输入特征自适应预测整数值激活，并在推理阶段将其转换为脉冲。该设计保留了事件数据固有的稀疏性与细粒度时空敏锐性，从而在不牺牲性能的前提下实现高效能耗。在 FE108、FELT 与 VisEvent 上的大量评估表明，SpikeTrack 在精度与效率两方面均超越最优跟踪器。此外，消融研究验证了各模块的贡献，凸显了脉冲驱动架构在未来视觉应用中的实际潜力。
英文原文摘要 1296 字符
Event cameras have attracted considerable attention for object tracking due to their microsecond-level temporal resolution and wide dynamic range, yet effectively harnessing spiking neural networks (SNNs) in this domain remains challenging. In this paper, we introduce SpikeTrack, a purely spike-driven framework for single-object tracking that addresses the shortcomings of RGB-based approaches in fast-motion or target appearance change. Central to SpikeTrack is the Multi-Search-sequence-and-Single-Template (MSST) training paradigm, which captures rich temporal dependencies, alongside a Dynamic Integer Leaky Integrate-and-Fire (DI-LIF) neuron that adaptively predicts integer-valued activations based on the input features during training and converts them into spikes during inference. Our design preserves the intrinsic sparsity and fine-grained spatiotemporal acuity of event data, resulting in efficient energy consumption without sacrificing performance. Extensive evaluations on FE108, FELT, and VisEvent demonstrate that SpikeTrack exceeds the performance of state-of-the-art trackers in both accuracy and efficiency. Furthermore, ablation studies validate each module's contribution, highlighting the practical potential of spike-driven architectures for future vision applications.