Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal processing, and biological plausibility. However, SNNs are highly sensitive to distribution shifts, which can significantly degrade their performance in real-world scenarios. Traditional test-time adaptation (TTA) methods designed for ANNs often fail to address the unique computational dynamics of SNNs, such as sparsity and temporal spiking behavior. To address these challenges, we propose SPike-Aware Consistency Enhancement (SPACE), the first source-free and single-instance TTA method specifically designed for SNNs. SPACE leverages the inherent spike dynamics of SNNs to maximize the consistency of spike-behavior-based local feature maps across augmented versions of a single test sample, enabling robust adaptation without requiring source data. We evaluate SPACE on multiple datasets. Furthermore, SPACE exhibits robust generalization across diverse network architectures, consistently enhancing the performance of SNNs on CNNs (such as VGG and ResNet), Transformer models, and ConvLSTM architectures. Experimental results show that SPACE outperforms state-of-the-art methods, highlighting its effectiveness and robustness in real-world settings.

翻译：脉冲神经网络（SNNs）作为人工神经网络（ANNs）的一种生物启发的替代方案，在能效、时序处理和生物合理性方面展现出优势。然而，SNNs对分布偏移高度敏感，这在实际场景中会显著降低其性能。为ANNs设计的传统测试时自适应（TTA）方法通常无法应对SNNs独特的计算动态特性，例如稀疏性和时序脉冲行为。为应对这些挑战，我们提出了脉冲感知一致性增强（SPACE），这是首个专为SNNs设计的无源单实例TTA方法。SPACE利用SNNs固有的脉冲动态特性，通过最大化单个测试样本增强版本间基于脉冲行为的局部特征图的一致性，实现无需源数据的鲁棒自适应。我们在多个数据集上评估了SPACE。此外，SPACE在不同网络架构上展现出强大的泛化能力，持续提升了SNNs在CNN（如VGG和ResNet）、Transformer模型以及ConvLSTM架构上的性能。实验结果表明，SPACE优于现有最先进方法，突显了其在实际场景中的有效性和鲁棒性。