首个利用脉冲网络时序特性的半监督学习框架，提升小样本场景下的模型性能。
SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
- 通过脉冲神经网络的漏电因子捕捉时序动态，实现多视角预测一致性伪标签生成。
- 在多个标准数据集上超越现有适配脉冲网络的半监督方法，显著提升小样本学习效果。
- 适合研究脉冲神经网络、低功耗机器学习或资源受限设备上的高效训练者。
脉冲神经网络（SNNs）因其生物合理性与能效优势受到广泛关注，但相比人工神经网络（ANNs），基于SNN的半监督学习（SSL）方法仍处于探索阶段。本文提出SpikeMatch，首个利用SNN时序动态的半监督学习框架，通过漏电因子构建多视角预测一致性，在协同训练框架中生成高质量伪标签。该方法从弱增强的无标签样本中生成可靠伪标签，用于强增强样本的训练，有效缓解了因标签有限导致的确认偏差问题。实验表明，SpikeMatch在多个标准基准测试中均优于现有适配SNN主干网络的半监督方法。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to those for artificial neural networks (ANNs). In this paper, we introduce SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics through the leakage factor of SNNs for diverse pseudo-labeling within a co-training framework. By utilizing agreement among multiple predictions from a single SNN, SpikeMatch generates reliable pseudo-labels from weakly-augmented unlabeled samples to train on strongly-augmented ones, effectively mitigating confirmation bias by capturing discriminative features with limited labels. Experiments show that SpikeMatch outperforms existing SSL methods adapted to SNN backbones across various standard benchmarks.
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。