SpikeTrack：面向高效视觉跟踪的脉冲驱动框架
SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking
把脉冲神经网络的不对称时间步扩展与单向信息流设计用于 RGB 跟踪，并用记忆检索模块在分支间传递模板线索；对做视觉跟踪或想在视觉任务中引入 SNN 低能耗计算的人，这是一套可直接借鉴的骨干与跨分支信息传递范式。
原文依据 SpikeTrack employs a novel asymmetric design that uses asymmetric timestep expansion and unidirectional information flow
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论脉冲神经网络（SNN）有望实现高能效视觉，但将其应用于 RGB 视觉跟踪仍然困难：现有 SNN 跟踪框架要么未与脉冲驱动计算完全对齐，要么未充分利用神经元的时空动力学，导致效率与精度之间难以兼顾。为解决这一问题，我们提出 SpikeTrack，一个面向高能效 RGB 目标跟踪的脉冲驱动框架。SpikeTrack 采用一种新颖的不对称设计，使用不对称时间步扩展与单向信息流，在利用时空动力学的同时降低计算量。为确保分支之间有效的单向信息传递，我们设计了一个受神经推理机制启发的记忆检索模块。该模块循环地查询一个由模板初始化的紧凑记忆，以检索目标线索并随时间增强目标感知。大量实验表明，SpikeTrack 在基于 SNN 的跟踪器中达到最优，并与先进的 ANN 跟踪器保持竞争力。值得注意的是，它在 LaSOT 数据集上超过 TransT，而能耗仅为其 1/26。据我们所知，SpikeTrack 是首个使 RGB 跟踪同时具备高精度与高能效的脉冲驱动框架。
英文原文摘要 1279 字符
Spiking Neural Networks (SNNs) promise energy-efficient vision, but applying them to RGB visual tracking remains difficult: Existing SNN tracking frameworks either do not fully align with spike-driven computation or do not fully leverage neurons' spatiotemporal dynamics, leading to a trade-off between efficiency and accuracy. To address this, we introduce SpikeTrack, a spike-driven framework for energy-efficient RGB object tracking. SpikeTrack employs a novel asymmetric design that uses asymmetric timestep expansion and unidirectional information flow, harnessing spatiotemporal dynamics while cutting computation. To ensure effective unidirectional information transfer between branches, we design a memory-retrieval module inspired by neural inference mechanisms. This module recurrently queries a compact memory initialized by the template to retrieve target cues and sharpen target perception over time. Extensive experiments demonstrate that SpikeTrack achieves the state-of-the-art among SNN-based trackers and remains competitive with advanced ANN trackers. Notably, it surpasses TransT on LaSOT dataset while consuming only 1/26 of its energy. To our knowledge, SpikeTrack is the first spike-driven framework to make RGB tracking both accurate and energy efficient.