提升脉冲神经网络表达能力，让其性能逼近甚至超过传统神经网络。
Integer Binary-Range Alignment Neuron for Spiking Neural Networks
- 用整数二进制对齐机制增强脉冲神经元信息表达能力。
- 在ImageNet上达74.19%准确率，超越此前最佳水平3.45%。
- 相同架构下媲美甚至超越人工神经网络，能效提升6.3倍。
脉冲神经网络（SNNs）因其类脑计算和高能效备受关注，但在图像分类与目标检测等任务上的表现仍落后于人工神经网络（ANNs），主要受限于表达能力不足。为此，本文提出一种新型脉冲神经元——整数二进制范围对齐漏电积分-放电神经元（Integer Binary-Range Alignment Leaky Integrate-and-Fire），通过整数激活与范围对齐策略，在仅轻微增加能耗的前提下，显著扩展神经元的信息表达能力。该方法在训练中支持整数激活，在推理时通过二值化实现虚拟时间步扩展，保持脉冲驱动动态；范围对齐策略有效缓解了神经元难以激活高整数值的问题。实验表明，本方法在ImageNet上达到74.19%准确率，在COCO数据集上取得66.2% mAP@50和49.1% mAP@50:95，分别优于此前最优结果3.45%、1.6%和1.8%。值得注意的是，该SNN在相同架构下性能可匹配甚至超越对应ANN，同时能效提升6.3倍。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) are noted for their brain-like computation and energy efficiency, but their performance lags behind Artificial Neural Networks (ANNs) in tasks like image classification and object detection due to the limited representational capacity. To address this, we propose a novel spiking neuron, Integer Binary-Range Alignment Leaky Integrate-and-Fire to exponentially expand the information expression capacity of spiking neurons with only a slight energy increase. This is achieved through Integer Binary Leaky Integrate-and-Fire and range alignment strategy. The Integer Binary Leaky Integrate-and-Fire allows integer value activation during training and maintains spike-driven dynamics with binary conversion expands virtual timesteps during inference. The range alignment strategy is designed to solve the spike activation limitation problem where neurons fail to activate high integer values. Experiments show our method outperforms previous SNNs, achieving 74.19% accuracy on ImageNet and 66.2% mAP@50 and 49.1% mAP@50:95 on COCO, surpassing previous bests with the same architecture by +3.45% and +1.6% and +1.8%, respectively. Notably, our SNNs match or exceed ANNs' performance with the same architecture, and the energy efficiency is improved by 6.3${\times}$.
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。