通过位运算分离稳定脉冲，提升脉冲神经网络的识别准确率
Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks
- 用位与操作分离稳定脉冲骨架与多时步脉冲，减少噪声干扰
- 在多个数据集上实现最高8.33%的准确率提升，尤其适合超低延迟场景
- 兼顾硬件友好性与模型泛化，适合部署于类脑计算系统
尽管脉冲神经网络（SNNs）的时序脉冲特性具备低功耗时序模式捕捉能力，但其固有的不一致性严重损害了表征性能。本文提出Stable Spike，通过双一致性优化缓解该问题，显著提升SNN的识别性能。利用硬件友好的“位与”操作，高效分离稳定脉冲骨架与多时步脉冲图，保留关键语义的同时降低由随机噪声脉冲带来的不一致性。强制不稳定的脉冲图向稳定脉冲骨架收敛，显著增强时步间的一致性。此外，向稳定脉冲骨架注入幅度感知的脉冲噪声，以丰富表示并保持语义一致性。模型被鼓励产生对扰动一致的预测，从而提升泛化能力。大量实验验证了方法的有效性与通用性。特别是在超低延迟条件下，本方法显著提升了类脑目标识别准确率，最高提升达8.33%，有助于充分释放SNN在功耗与速度上的潜力。
原文摘要 · Abstract (English)
Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal pattern 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, thereby capturing critical semantics while reducing inconsistencies 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。