Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Qi, Zhu, Junyang, Zhou, Dongdong, Chen, Hao, Liu, Yang, Shen, Jiangrong, Zhang, Qiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918021110431744
author Xu, Qi
Zhu, Junyang
Zhou, Dongdong
Chen, Hao
Liu, Yang
Shen, Jiangrong
Zhang, Qiang
author_facet Xu, Qi
Zhu, Junyang
Zhou, Dongdong
Chen, Hao
Liu, Yang
Shen, Jiangrong
Zhang, Qiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07921
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
Xu, Qi
Zhu, Junyang
Zhou, Dongdong
Chen, Hao
Liu, Yang
Shen, Jiangrong
Zhang, Qiang
Machine Learning
Artificial Intelligence
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.
title Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.07921