Abstract
Neuromorphic vision systems based on spiking neural networks (SNNs) offer ultra-low-power perception for event-based and frame-based cameras, yet catastrophic forgetting remains a critical barrier to deployment in continually evolving environments. Existing continual learning methods, developed primarily for artificial neural networks, seldom jointly optimize accuracy and energy efficiency, with particularly limited exploration on event-based datasets. We propose an energy-aware spike budgeting framework for continual SNN learning that integrates experience replay, learnable leaky integrate-and-fire neuron parameters, and an adaptive spike scheduler to enforce dataset-specific energy constraints during training. Our approach exhibits modality-dependent behavior: on frame-based datasets (MNIST, CIFAR-10), spike budgeting acts as a sparsity-inducing regularizer, improving accuracy while reducing spike rates by up to 47\%; on event-based datasets (DVS-Gesture, N-MNIST, CIFAR-10-DVS), controlled budget relaxation enables accuracy gains up to 17.45 percentage points with minimal computational overhead. Across five benchmarks spanning both modalities, our method demonstrates consistent performance improvements while minimizing dynamic power consumption, advancing the practical viability of continual learning in neuromorphic vision systems.
Abstract (translated)
基于脉冲神经网络（SNN）的类脑视觉系统为事件驱动和帧基摄像头提供了超低功耗感知能力，但灾难性遗忘仍然是在不断变化环境中部署的关键障碍。现有的持续学习方法主要是针对人工神经网络开发的，很少同时优化准确性和能源效率，并且对事件数据集的研究尤其有限。我们提出了一种能耗感知的脉冲预算框架，用于连续SNN学习，该框架结合了经验回放、可学习的漏电积分发放神经元参数以及自适应脉冲调度器，在训练过程中执行特定于数据集的能量约束。我们的方法表现出模态依赖性行为：在帧基数据集（MNIST, CIFAR-10）上，脉冲预算起到了促进稀疏性的正则化作用，提高了准确性同时将脉冲率减少了最多47%；而在事件驱动的数据集（DVS-Gesture, N-MNIST, CIFAR-10-DVS）上，控制性预算放松能够使准确度提升高达17.45个百分点，并且计算开销极小。在横跨两种模态的五个基准测试中，我们的方法展示了一致性的性能改进并同时最小化了动态功耗，从而推进了类脑视觉系统中持续学习的实际可行性。
URL
https://arxiv.org/abs/2602.12236
