Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

• URL: http://arxiv.org/abs/2604.08894v1
• Date: Fri, 10 Apr 2026 02:58:46 GMT
• Title: Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer
• Abstract summary: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs)<n>Existing paradigms including ANN-SNN Conversion and Spatial-Temporal Backpropagation (STBP) suffer from inherent limitations.<n>We propose Ge$text2$mS-T, a novel architecture implementing grouped computation across temporal, spatial and network structure dimensions.
• Score: 84.8831358775386
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment [52.910770415431244]
  Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing.<n>ANN-SNN conversion circumvents issues by reusing well-trained ANN weights for low-latency, energy-efficient inference.<n>Existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors.
  arXiv  Detail & Related papers  (2026-08-14T04:46:03Z)
• Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks [9.353524841177316]
  We focus on image classification, a core task in computer vision, especially in low-resource environments.<n>Our approach led to significantly better configurations of DSNNs regarding loss and emissions compared to default DSNNs.<n>Investigating the behavior of quantized networks in terms of both emissions and accuracy, our experiments reveal surprising model-specific trade-offs, yielding the greatest energy savings.
  arXiv  Detail & Related papers  (2026-06-22T11:53:42Z)
• ReSCom: A Reconfigurable Spiking Neural Network Accelerator Using Stochastic Computing [0.0]
  ReSCom is a reconfigurable SNN accelerator that reduces hardware complexity while maintaining stable inference.<n>A unified reconfigurable design supports Integrate-and-Fire, Leaky-and-Fire, and Synaptic neuron models within a single hardware framework.
  arXiv  Detail & Related papers  (2026-06-11T16:44:08Z)
• DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement [64.23650268245822]
  This work propose a DualBranch Hybrid Neural (DBHN) Network.<n>A dual-branch network integrating ANN and SNN was designed, where the SNN branch reduces power consumption while the ANN branch addresses information loss.<n>Results show that the proposed model maintains superior performance across three public datasets while achieving an average fold reduction in computational complexity.
  arXiv  Detail & Related papers  (2026-06-04T09:16:26Z)
• Neural Dynamics Self-Attention for Spiking Transformers [59.57278823240336]
  Spiking Neural Networks (SNNs) with Transformer architectures offer a promising pathway to balance energy efficiency and performance.<n>Existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference.<n>We propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements.
  arXiv  Detail & Related papers  (2026-03-09T12:23:37Z)
• ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages [0.0]
  Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies.<n>We propose the Efficient Convolutional Vision Transformer (ECViT), a hybrid architecture that effectively combines the strengths of CNNs and Transformers.
  arXiv  Detail & Related papers  (2025-04-21T03:00:17Z)
• BHViT: Binarized Hybrid Vision Transformer [53.38894971164072]
  Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN)<n>We propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations.<n>Our proposed algorithm achieves SOTA performance among binary ViT methods.
  arXiv  Detail & Related papers  (2025-03-04T08:35:01Z)
• Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks [44.145870290310356]
  Spiking Neural Networks have attracted significant attention in recent years due to their distinctive low-power characteristics.<n>Transformers models, known for their powerful self-attention mechanisms and parallel processing capabilities, have demonstrated exceptional performance across various domains.<n>Despite the significant advantages of both SNNs and Transformers, directly combining the low-power benefits of SNNs with the high performance of Transformers remains challenging.
  arXiv  Detail & Related papers  (2024-12-18T07:07:38Z)
• Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-Resolution [6.857919231112562]
  Window-based transformers have demonstrated outstanding performance in super-resolution tasks. They exhibit higher computational complexity and inference latency than convolutional neural networks. We construct a convolution-based Transformer framework named the linear adaptive mixer network (LAMNet)
  arXiv  Detail & Related papers  (2024-09-26T07:24:09Z)
• LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization [48.41286573672824]
  Spiking Neural Networks (SNNs) mimic the information-processing mechanisms of the human brain and are highly energy-efficient. We propose a new approach named LitE-SNN that incorporates both spatial and temporal compression into the automated network design process.
  arXiv  Detail & Related papers  (2024-01-26T05:23:11Z)
• AutoST: Training-free Neural Architecture Search for Spiking Transformers [14.791412391584064]
  Spiking Transformers achieve both the energy efficiency of Spiking Neural Networks (SNNs) and the high capacity of Transformers. Existing Spiking Transformer architectures exhibit a notable architectural gap, resulting in suboptimal performance. We introduce AutoST, a training-free NAS method for Spiking Transformers, to rapidly identify high-performance Spiking Transformer architectures.
  arXiv  Detail & Related papers  (2023-07-01T10:19:52Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization [4.0554893636822]
  We introduce a novel approach to deploy large-scale Deep Neural Networks on constrained resources. The method speeds up inference time and aims to reduce memory demand and power consumption.
  arXiv  Detail & Related papers  (2022-12-25T15:40:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.