# Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block

arXiv: https://arxiv.org/abs/2203.10006 · HTML: https://mlsanity.com/paper/2203.10006/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks](https://mlsanity.com/paper/2002.10085/) (2020)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization](https://mlsanity.com/paper/1911.00822/) (2019)
- [Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks](https://mlsanity.com/paper/1908.06378/) (2019)
- [Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks](https://mlsanity.com/paper/1805.07866/) (2018)
- [Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2110.08858/) (2021)
- [BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons](https://mlsanity.com/paper/2105.13004/) (2021)
- [Spatiotemporal Filtering for Event-Based Action Recognition](https://mlsanity.com/paper/1903.07067/) (2019)
- [Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks?](https://mlsanity.com/paper/2112.12133/) (2021)
- [HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2107.11979/) (2021)
- [Direct Training via Backpropagation for Ultra-low Latency Spiking Neural Networks with Multi-threshold](https://mlsanity.com/paper/2112.07426/) (2021)
- [Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators using Time Compression Supporting Multiple Spike Codes](https://mlsanity.com/paper/1909.04757/) (2019)

## Built on by (most cited first, 4 of 4)

- [Deep Multi-Threshold Spiking-UNet for Image Processing](https://mlsanity.com/paper/2307.10974/) (2023)
- [FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks](https://mlsanity.com/paper/2507.23643/) (2025)
- [ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference](https://mlsanity.com/paper/2508.01223/) (2025)
- [SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization](https://mlsanity.com/paper/2508.10913/) (2025)

## Abstract (arXiv)

Spiking neural networks (SNNs), as one of the brain-inspired models, has spatio-temporal information processing capability, low power feature, and high biological plausibility. The effective spatio-temporal feature makes it suitable for event streams classification. However, neuromorphic datasets, such as N-MNIST, CIFAR10-DVS, DVS128-gesture, need to aggregate individual events into frames with a new higher temporal resolution for event stream classification, which causes high training and inference latency. In this work, we proposed a spatio-temporal compression method to aggregate individual events into a few time steps of synaptic current to reduce the training and inference latency. To keep the accuracy of SNNs under high compression ratios, we also proposed a synaptic convolutional block to balance the dramatic change between adjacent time steps. And multi-threshold Leaky Integrate-and-Fire (LIF) with learnable membrane time constant is introduced to increase its information processing capability. We evaluate the proposed method for event streams classification tasks on neuromorphic N-MNIST, CIFAR10-DVS, DVS128 gesture datasets. The experiment results show that our proposed method outperforms the state-of-the-art accuracy on nearly all datasets, using fewer time steps.