# STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2503.02689 · HTML: https://mlsanity.com/paper/2503.02689/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 73 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures](https://mlsanity.com/paper/1903.06379/) (2019)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Efficient Neuromorphic Signal Processing with Loihi 2](https://mlsanity.com/paper/2111.03746/) (2021)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks](https://mlsanity.com/paper/2206.10177/) (2022)
- [Membrane Potential Batch Normalization for Spiking Neural Networks](https://mlsanity.com/paper/2308.08359/) (2023)
- [A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/2104.10719/) (2021)
- [Line-based 6-DoF Object Pose Estimation and Tracking With an Event Camera](https://mlsanity.com/paper/2408.03225/) (2024)
- [Brain-inspired global-local learning incorporated with neuromorphic computing](https://mlsanity.com/paper/2006.03226/) (2020)
- [RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks](https://mlsanity.com/paper/2308.06787/) (2023)
- [Training Full Spike Neural Networks via Auxiliary Accumulation Pathway](https://mlsanity.com/paper/2301.11929/) (2023)
- [Real Spike: Learning Real-valued Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2210.06686/) (2022)

## Built on by (most cited first, 11 of 11)

- [TS-SNN: Temporal Shift Module for Spiking Neural Networks](https://mlsanity.com/paper/2505.04165/) (2025)
- [SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaboration](https://mlsanity.com/paper/2508.02069/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers](https://mlsanity.com/paper/2510.07924/) (2025)
- [ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs](https://mlsanity.com/paper/2602.01124/) (2026)
- [SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks](https://mlsanity.com/paper/2606.27807/) (2026)
- [Efficient Aspect Term Extraction using Spiking Neural Network](https://mlsanity.com/paper/2601.06637/) (2026)
- [Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks](https://mlsanity.com/paper/2603.11676/) (2026)
- [Learnable Burst Quantization for Expressive and Efficient Spiking Neural Networks](https://mlsanity.com/paper/2604.25688/) (2026)
- [SAFformer:Improving Spiking Transformer via Active Predictive Filtering](https://mlsanity.com/paper/2605.08270/) (2026)
- [A Robust Point Cloud Analysis Framework Inspired By Primary Visual Cortex](https://mlsanity.com/paper/2606.14292/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have gained significant attention due to their biological plausibility and energy efficiency, making them promising alternatives to Artificial Neural Networks (ANNs). However, the performance gap between SNNs and ANNs remains a substantial challenge hindering the widespread adoption of SNNs. In this paper, we propose a Spatial-Temporal Attention Aggregator SNN (STAA-SNN) framework, which dynamically focuses on and captures both spatial and temporal dependencies. First, we introduce a spike-driven self-attention mechanism specifically designed for SNNs. Additionally, we pioneeringly incorporate position encoding to integrate latent temporal relationships into the incoming features. For spatial-temporal information aggregation, we employ step attention to selectively amplify relevant features at different steps. Finally, we implement a time-step random dropout strategy to avoid local optima. As a result, STAA-SNN effectively captures both spatial and temporal dependencies, enabling the model to analyze complex patterns and make accurate predictions. The framework demonstrates exceptional performance across diverse datasets and exhibits strong generalization capabilities. Notably, STAA-SNN achieves state-of-the-art results on neuromorphic datasets CIFAR10-DVS, with remarkable performances of 97.14%, 82.05% and 70.40% on the static datasets CIFAR-10, CIFAR-100 and ImageNet, respectively. Furthermore, our model exhibits improved performance ranging from 0.33% to 2.80% with fewer time steps. The code for the model is available on GitHub.