Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
This work addresses the challenge of making SNNs more effective for few-shot learning, which is important for applications with limited data, though it appears incremental as it builds upon existing SNN methods.
The authors tackled the problem of improving few-shot learning performance and efficiency in Spiking Neural Networks (SNNs) by proposing a framework that combines self-feature extraction and cross-feature contrastive modules, resulting in significant classification improvements on the N-Omniglot dataset and competitive performance on CUB and miniImageNet with low power consumption.
Deep neural networks (DNNs) excel in computer vision tasks, especially, few-shot learning (FSL), which is increasingly important for generalizing from limited examples. However, DNNs are computationally expensive with scalability issues in real world. Spiking Neural Networks (SNNs), with their event-driven nature and low energy consumption, are particularly efficient in processing sparse and dynamic data, though they still encounter difficulties in capturing complex spatiotemporal features and performing accurate cross-class comparisons. To further enhance the performance and efficiency of SNNs in few-shot learning, we propose a few-shot learning framework based on SNNs, which combines a self-feature extractor module and a cross-feature contrastive module to refine feature representation and reduce power consumption. We apply the combination of temporal efficient training loss and InfoNCE loss to optimize the temporal dynamics of spike trains and enhance the discriminative power. Experimental results show that the proposed FSL-SNN significantly improves the classification performance on the neuromorphic dataset N-Omniglot, and also achieves competitive performance to ANNs on static datasets such as CUB and miniImageNet with low power consumption.