面向边缘设备的稀疏感知脉冲神经网络，实现低能耗少样本增量学习。
SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
- 通过阈值调节实现神经元动态稀疏，自然保留旧类知识。
- 在Mini-ImageNet上最后阶段性能提升至少4.01%，能量消耗降低20%。
- 适合资源受限的边缘设备部署，尤其适用于少样本场景。
持续学习新类别对边缘设备保护数据隐私、维持动态环境下的可靠性能至关重要。然而，在数据样本不足时，实现设备端少样本增量学习（FSCIL）极具挑战。现有基于人工神经网络（ANN）的高效框架仍受设备资源限制。脉冲神经网络（SNN）能高效处理时空信息，具有更低能耗、更强生物合理性及与类脑硬件兼容性。本文提出一种基于SNN的方法SAFA-SNN，包含稀疏感知神经动力学与快速自适应结构。通过阈值调节，多数神经元保持稳定放电，少数呈现自适应放电，从而自然保存编码基础类知识的突触痕迹，缓解灾难性遗忘。针对反向传播中脉冲不可微问题，采用零阶优化等无梯度方法。同时，为克服类别原型在少量数据上过拟合并引入偏差的问题，通过正交子空间投影增强原型判别力。在两个标准数据集（CIFAR-100和Mini-ImageNet）以及三个类脑数据集（CIFAR10-DVS、DVS128 Gesture、N-Caltech101）上的大量实验表明，SAFA-SNN优于基线方法，尤其在Mini-ImageNet上最后增量阶段性能提升至少4.01%，在CIFAR-100上能量消耗降低20%，具备实际部署可行性。
原文摘要 · Abstract (English)
Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments. However, the scenario becomes particularly challenging when data samples are insufficient, requiring on-device few-shot class-incremental learning (FSCIL). Although existing work has explored parameter-efficient FSCIL frameworks based on artificial neural networks (ANNs), their deployment is still fundamentally constrained by limited device resources. Spiking neural networks (SNNs) process spatiotemporal information efficiently, offering lower energy consumption, greater biological plausibility, and compatibility with neuromorphic hardware than ANNs. In this work, we propose an SNN-based method containing Sparsity-Aware neuronal dynamics and Fast Adaptive structure (SAFA-SNN) for on-device FSCIL. By threshold regulation, most neurons exhibit stable spikes and others exhibit adaptive spikes. As a result, synaptic traces that encode base-class knowledge are naturally preserved, thereby alleviating catastrophic forgetting. To cope with spike non-differentiability in backpropagation, we employ a gradient-free technique, i.e., zeroth-order optimization. Moreover, class prototypes can limit overfitting on few-shot data but introduce bias. We enhance prototype discriminability by orthogonal subspace projection. Extensive experiments conducted on two standard benchmark datasets (CIFAR-100 and Mini-ImageNet) and three neuromorphic datasets (CIFAR10-DVS, DVS128 Gesture, and N-Caltech101) demonstrate that SAFA-SNN outperforms baselines, specifically achieving at least 4.01% improvement at the last incremental session on Mini-ImageNet and 20% lower energy cost on CIFAR-100 over baselines with practical implementation.
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。