通过时空自注意力对齐，提升神经网络到脉冲网络的知识迁移精度。
Self-Attentive Spatio-Temporal Calibration for Precise Intermediate Layer Matching in ANN-to-SNN Distillation
- 用自注意力机制自动匹配ANN与SNN的时空语义层
- 在CIFAR-10上达95.12%准确率，首次超越ANN
- 适合低功耗部署场景下的高精度脉冲网络设计
脉冲神经网络（SNN）因事件驱动机制具备低功耗潜力，但通常精度低于人工神经网络（ANN）。现有从ANN到SNN的知识蒸馏方法或仅依赖标签信息，忽略中间层特征，或采用逐层方法，忽视空间与时间语义不一致，导致性能下降。为此，本文提出自注意力时空校准（SASTC）方法，利用自注意力识别ANN与SNN之间在空间和时间上的语义对齐层对，实现语义信息的自主传递。大量实验表明，SASTC显著优于现有方法，有效解决层间错配问题。在静态数据集上表现优异：CIFAR-10达95.12%，CIFAR-100（2个时间步）达79.40%，ImageNet（4个时间步）达68.69%；在类脑数据集上，DVS-Gesture达97.92%，DVS-CIFAR10达83.60%。这是SNN首次在CIFAR-10和CIFAR-100上超越ANN，为SNN的应用前景带来新突破。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) are promising for low-power computation due to their event-driven mechanism but often suffer from lower accuracy compared to Artificial Neural Networks (ANNs). ANN-to-SNN knowledge distillation can improve SNN performance, but previous methods either focus solely on label information, missing valuable intermediate layer features, or use a layer-wise approach that neglects spatial and temporal semantic inconsistencies, leading to performance degradation.To address these limitations, we propose a novel method called self-attentive spatio-temporal calibration (SASTC). SASTC uses self-attention to identify semantically aligned layer pairs between ANN and SNN, both spatially and temporally. This enables the autonomous transfer of relevant semantic information. Extensive experiments show that SASTC outperforms existing methods, effectively solving the mismatching problem. Superior accuracy results include 95.12% on CIFAR-10, 79.40% on CIFAR-100 with 2 time steps, and 68.69% on ImageNet with 4 time steps for static datasets, and 97.92% on DVS-Gesture and 83.60% on DVS-CIFAR10 for neuromorphic datasets. This marks the first time SNNs have outperformed ANNs on both CIFAR-10 and CIFAR-100, shedding the new light on the potential applications 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。