AI 中文总结
该研究针对ANN-SNN转换的小时间步长准确率下降问题，提出残差膜电位对齐策略，结合动态初始电位调优、特征增强与SCR-Conv2d层，在T=2、4、8时显著提升准确率且开销可忽略。
AI 中文摘要
脉冲神经网络（SNN）凭借事件驱动的运行机制和极低的功耗，成为神经形态计算的核心架构。直接训练SNN会因不可微分的脉冲导致梯度消失和优化不稳定问题，而人工神经网络（ANN）到SNN的转换方法可复用已训练好的ANN权重，实现低延迟、高能效的推理，从而规避上述问题。不过，现有转换方案在小时间步长下存在严重的准确率下降，还会带来较大的推理延迟和累积量化误差，仅在大时间步长T下性能损失较小。为解决这些局限，我们首先从残差膜电位统计角度分析传统转换流程的缺陷，提出结合动态初始电位调优与特征增强的新型转换策略；接着引入正则化损失$\boldsymbol{\textit{L}}_{\text{RMPD}}$，用于适配IF神经元的初始电位，缓解边界聚合带来的系统性截断偏差；进一步构建带分组卷积的专用SCR-Conv2d竞争优化层，以增强特征辨识度、消除冗余脉冲并在极短时间窗口下稳定编码。结合当前最先进的QCFS基准，我们的方法实现了稳定的低延迟性能提升，且可泛化到ReLU卷积神经网络（CNN）、ANN Transformer及多阈值SNN变体。在CIFAR-10、CIFAR-100和ImageNet上的评估验证了，在T=2、4、8时均有显著的准确率提升，且额外计算开销可忽略。本研究提供了一种有效的转换范式，助力SNN在神经形态芯片上的实际部署。
英文摘要
Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing thanks to event-driven operation and ultra-low power consumption. Direct SNN training is hindered by non-differentiable spikes that induce vanishing gradients and unstable optimization. ANN-SNN conversion circumvents such issues by reusing well-trained ANN weights for low-latency, energy-efficient inference. Nevertheless, existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors, even with marginal performance loss at large $T$. To address these limitations, we first analyze flaws of conventional conversion pipelines from residual membrane potential statistics and propose a novel conversion strategy combining dynamic initial potential tuning and feature enhancement. We then introduce a regularization loss $\mathcal{L}_{\mathrm{RMPD}}$ to adapt initial potential of IF neurons and mitigate systematic truncation bias from boundary aggregation. A dedicated SCR-Conv2d competitive refinement layer with grouped convolution is further built to sharpen feature discrimination, eliminate redundant spikes and stabilize encoding under tiny time windows. Integrated with the state-of-the-art QCFS baseline, our approach delivers consistent low-latency performance gains and generalizes to ReLU CNNs, ANN Transformers, and multi-threshold SNN variants. Evaluations on CIFAR-10, CIFAR-100 and ImageNet verify prominent accuracy improvements at $T=2,4,8$, with negligible extra computation overhead. This work offers an effective conversion paradigm to facilitate real-world SNN deployment on neuromorphic chips.
