Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929303642439680 |
|---|---|
| author | Yao, Man Hu, Jiakui Hu, Tianxiang Xu, Yifan Zhou, Zhaokun Tian, Yonghong Xu, Bo Li, Guoqi |
| author_facet | Yao, Man Hu, Jiakui Hu, Tianxiang Xu, Yifan Zhou, Zhaokun Tian, Yonghong Xu, Bo Li, Guoqi |
| contents | Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the current mainstream of neuromorphic computing. By contrast, no neuromorphic chips are designed especially for Transformer-based SNNs, which have just emerged, and their performance is only on par with CNN-based SNNs, offering no distinct advantage. In this work, we propose a general Transformer-based SNN architecture, termed as ``Meta-SpikeFormer", whose goals are: 1) Lower-power, supports the spike-driven paradigm that there is only sparse addition in the network; 2) Versatility, handles various vision tasks; 3) High-performance, shows overwhelming performance advantages over CNN-based SNNs; 4) Meta-architecture, provides inspiration for future next-generation Transformer-based neuromorphic chip designs. Specifically, we extend the Spike-driven Transformer in \citet{yao2023spike} into a meta architecture, and explore the impact of structure, spike-driven self-attention, and skip connection on its performance. On ImageNet-1K, Meta-SpikeFormer achieves 80.0\% top-1 accuracy (55M), surpassing the current state-of-the-art (SOTA) SNN baselines (66M) by 3.7\%. This is the first direct training SNN backbone that can simultaneously supports classification, detection, and segmentation, obtaining SOTA results in SNNs. Finally, we discuss the inspiration of the meta SNN architecture for neuromorphic chip design. Source code and models are available at \url{https://github.com/BICLab/Spike-Driven-Transformer-V2}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03663 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips Yao, Man Hu, Jiakui Hu, Tianxiang Xu, Yifan Zhou, Zhaokun Tian, Yonghong Xu, Bo Li, Guoqi Neural and Evolutionary Computing Computer Vision and Pattern Recognition Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the current mainstream of neuromorphic computing. By contrast, no neuromorphic chips are designed especially for Transformer-based SNNs, which have just emerged, and their performance is only on par with CNN-based SNNs, offering no distinct advantage. In this work, we propose a general Transformer-based SNN architecture, termed as ``Meta-SpikeFormer", whose goals are: 1) Lower-power, supports the spike-driven paradigm that there is only sparse addition in the network; 2) Versatility, handles various vision tasks; 3) High-performance, shows overwhelming performance advantages over CNN-based SNNs; 4) Meta-architecture, provides inspiration for future next-generation Transformer-based neuromorphic chip designs. Specifically, we extend the Spike-driven Transformer in \citet{yao2023spike} into a meta architecture, and explore the impact of structure, spike-driven self-attention, and skip connection on its performance. On ImageNet-1K, Meta-SpikeFormer achieves 80.0\% top-1 accuracy (55M), surpassing the current state-of-the-art (SOTA) SNN baselines (66M) by 3.7\%. This is the first direct training SNN backbone that can simultaneously supports classification, detection, and segmentation, obtaining SOTA results in SNNs. Finally, we discuss the inspiration of the meta SNN architecture for neuromorphic chip design. Source code and models are available at \url{https://github.com/BICLab/Spike-Driven-Transformer-V2}. |
| title | Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips |
| topic | Neural and Evolutionary Computing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.03663 |