Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918438151127040 |
|---|---|
| author | Hao, Zecheng Xie, Shenghao Chen, Kang Liu, Wenxuan Yu, Zhaofei Huang, Tiejun |
| author_facet | Hao, Zecheng Xie, Shenghao Chen, Kang Liu, Wenxuan Yu, Zhaofei Huang, Tiejun |
| contents | Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and inference metrics when applied to Spiking Vision Transformers (S-ViTs). Existing paradigms including ANN-SNN Conversion and Spatial-Temporal Backpropagation (STBP) suffer from inherent limitations, precluding concurrent optimization of memory, accuracy and energy consumption. To address these issues, we propose Ge$^\text{2}$mS-T, a novel architecture implementing grouped computation across temporal, spatial and network structure dimensions. Specifically, we introduce the Grouped-Exponential-Coding-based IF (ExpG-IF) model, enabling lossless conversion with constant training overhead and precise regulation for spike patterns. Additionally, we develop Group-wise Spiking Self-Attention (GW-SSA) to reduce computational complexity via multi-scale token grouping and multiplication-free operations within a hybrid attention-convolution framework. Experiments confirm that our method can achieve superior performance with ultra-high energy efficiency on challenging benchmarks. To our best knowledge, this is the first work to systematically establish multi-dimensional grouped computation for resolving the triad of memory overhead, learning capability and energy budget in S-ViTs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08894 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer Hao, Zecheng Xie, Shenghao Chen, Kang Liu, Wenxuan Yu, Zhaofei Huang, Tiejun Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and inference metrics when applied to Spiking Vision Transformers (S-ViTs). Existing paradigms including ANN-SNN Conversion and Spatial-Temporal Backpropagation (STBP) suffer from inherent limitations, precluding concurrent optimization of memory, accuracy and energy consumption. To address these issues, we propose Ge$^\text{2}$mS-T, a novel architecture implementing grouped computation across temporal, spatial and network structure dimensions. Specifically, we introduce the Grouped-Exponential-Coding-based IF (ExpG-IF) model, enabling lossless conversion with constant training overhead and precise regulation for spike patterns. Additionally, we develop Group-wise Spiking Self-Attention (GW-SSA) to reduce computational complexity via multi-scale token grouping and multiplication-free operations within a hybrid attention-convolution framework. Experiments confirm that our method can achieve superior performance with ultra-high energy efficiency on challenging benchmarks. To our best knowledge, this is the first work to systematically establish multi-dimensional grouped computation for resolving the triad of memory overhead, learning capability and energy budget in S-ViTs. |
| title | Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08894 |