Stable Spike：基于按位与运算的脉冲神经网络双重一致性优化
Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks
用按位与操作从多时间步脉冲图中解耦出稳定脉冲骨架，并以此作为一致性目标约束不稳定脉冲图，这一思路可迁移到任何需要跨时间步表征一致性的视觉模型（如视频/事件相机骨干网络）中，作为无需额外标注的表示正则手段。
原文依据 we efficiently decouple the stable spike skeleton from the multi-timestep spike maps
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管脉冲神经网络（SNN）的时序脉冲动力学带来了低功耗的时序捕捉能力，但它也引入了固有的不一致性，严重损害了表征质量。本文通过 Stable Spike 进行双重一致性优化以缓解该问题，从而提升 SNN 的识别性能。借助硬件友好的“与”按位运算，我们高效地从多时间步脉冲图中解耦出稳定脉冲骨架，该骨架捕捉了关键语义并减少了由多变噪声脉冲带来的不一致性。强制不稳定脉冲图向稳定脉冲骨架收敛，显著提升了跨时间步的固有一致性。此外，我们向稳定脉冲骨架注入幅度感知的脉冲噪声，以在保持语义一致的同时使表征多样化。SNN 被促使产生对扰动一致的预测，从而有助于泛化。在多种架构和数据集上的大量实验验证了本方法的有效性与通用性。特别地，我们的方法在超低延迟下的神经形态目标识别上取得显著进展，准确率最高提升 8.33%。这将有助于释放 SNN 的全部功耗与速度潜力。
英文原文摘要 1327 字符
Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal capture capabilities, they also incur inherent inconsistencies that severely compromise representation. In this paper, we perform dual consistency optimization via Stable Spike to mitigate this problem, thereby improving the recognition performance of SNNs. With the hardware-friendly "AND" bit operation, we efficiently decouple the stable spike skeleton from the multi-timestep spike maps, which captures critical semantics and reduces the inconsistency from variable noise spikes. Enforcing the unstable spike maps to converge to the stable spike skeleton significantly improves the inherent consistency across timesteps. Furthermore, we inject amplitude-aware spike noise into the stable spike skeleton to diversify the representations while preserving consistent semantics. The SNN is encouraged to produce perturbation-consistent predictions, thereby contributing to generalization. Extensive experiments across multiple architectures and datasets validate the effectiveness and versatility of our method. In particular, our method significantly advances neuromorphic object recognition under ultra-low latency, improving accuracy by up to 8.33%. This will help unlock the full power consumption and speed potential of SNNs.