提出新型脉冲神经网络模型，提升时空信息处理能力
DA-LIF: Dual Adaptive Leaky Integrate-and-Fire Model for Deep Spiking Neural Networks
- 引入可学习的空间与时间衰减参数，增强神经元多样性建模
- 在多个数据集上用更少时步达到更高精度，参数增量极小
- 适合低功耗神经形态计算，特别适用于实时动态视觉任务
脉冲神经网络（SNNs）因其高效处理时空信息的能力，具有生物合理性、低功耗和与神经形态硬件兼容的优势。然而，常用的漏积分-放电（LIF）模型忽略了神经元异质性，且独立处理空间与时间信息，限制了SNN的表达能力。本文提出双适应性漏积分-放电（DA-LIF）模型，通过引入可独立学习的空间与时间衰减参数，实现对神经元特性的动态调节。在静态数据集（CIFAR10/100、ImageNet）和神经形态数据集（CIFAR10-DVS、DVS128 Gesture）上的实验表明，相比现有最优方法，DA-LIF在更少的时步内实现了更高的准确率。更重要的是，该模型仅需极少额外参数，保持了低功耗特性。大量消融实验进一步验证了其鲁棒性与有效性。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) are valued for their ability to process spatio-temporal information efficiently, offering biological plausibility, low energy consumption, and compatibility with neuromorphic hardware. However, the commonly used Leaky Integrate-and-Fire (LIF) model overlooks neuron heterogeneity and independently processes spatial and temporal information, limiting the expressive power of SNNs. In this paper, we propose the Dual Adaptive Leaky Integrate-and-Fire (DA-LIF) model, which introduces spatial and temporal tuning with independently learnable decays. Evaluations on both static (CIFAR10/100, ImageNet) and neuromorphic datasets (CIFAR10-DVS, DVS128 Gesture) demonstrate superior accuracy with fewer timesteps compared to state-of-the-art methods. Importantly, DA-LIF achieves these improvements with minimal additional parameters, maintaining low energy consumption. Extensive ablation studies further highlight the robustness and effectiveness of the DA-LIF model.
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。