Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.06305 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909233833836544 |
|---|---|
| author | Ma, Yuqi Wang, Huamin Shen, Hangchi Chen, Xuemei Duan, Shukai Wen, Shiping |
| author_facet | Ma, Yuqi Wang, Huamin Shen, Hangchi Chen, Xuemei Duan, Shukai Wen, Shiping |
| contents | Recently, brain-inspired spiking neural networks (SNNs) have attracted great research attention owing to their inherent bio-interpretability, event-triggered properties and powerful perception of spatiotemporal information, which is beneficial to handling event-based neuromorphic datasets. In contrast to conventional static image datasets, event-based neuromorphic datasets present heightened complexity in feature extraction due to their distinctive time series and sparsity characteristics, which influences their classification accuracy. To overcome this challenge, a novel approach termed Neuromorphic Momentum Contrast Learning (NeuroMoCo) for SNNs is introduced in this paper by extending the benefits of self-supervised pre-training to SNNs to effectively stimulate their potential. This is the first time that self-supervised learning (SSL) based on momentum contrastive learning is realized in SNNs. In addition, we devise a novel loss function named MixInfoNCE tailored to their temporal characteristics to further increase the classification accuracy of neuromorphic datasets, which is verified through rigorous ablation experiments. Finally, experiments on DVS-CIFAR10, DVS128Gesture and N-Caltech101 have shown that NeuroMoCo of this paper establishes new state-of-the-art (SOTA) benchmarks: 83.6% (Spikformer-2-256), 98.62% (Spikformer-2-256), and 84.4% (SEW-ResNet-18), respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06305 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks Ma, Yuqi Wang, Huamin Shen, Hangchi Chen, Xuemei Duan, Shukai Wen, Shiping Computer Vision and Pattern Recognition Artificial Intelligence Recently, brain-inspired spiking neural networks (SNNs) have attracted great research attention owing to their inherent bio-interpretability, event-triggered properties and powerful perception of spatiotemporal information, which is beneficial to handling event-based neuromorphic datasets. In contrast to conventional static image datasets, event-based neuromorphic datasets present heightened complexity in feature extraction due to their distinctive time series and sparsity characteristics, which influences their classification accuracy. To overcome this challenge, a novel approach termed Neuromorphic Momentum Contrast Learning (NeuroMoCo) for SNNs is introduced in this paper by extending the benefits of self-supervised pre-training to SNNs to effectively stimulate their potential. This is the first time that self-supervised learning (SSL) based on momentum contrastive learning is realized in SNNs. In addition, we devise a novel loss function named MixInfoNCE tailored to their temporal characteristics to further increase the classification accuracy of neuromorphic datasets, which is verified through rigorous ablation experiments. Finally, experiments on DVS-CIFAR10, DVS128Gesture and N-Caltech101 have shown that NeuroMoCo of this paper establishes new state-of-the-art (SOTA) benchmarks: 83.6% (Spikformer-2-256), 98.62% (Spikformer-2-256), and 84.4% (SEW-ResNet-18), respectively. |
| title | NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2406.06305 |