# Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Network

arXiv: https://arxiv.org/abs/2401.01912 · HTML: https://mlsanity.com/paper/2401.01912/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 2 Jan 2024.

## Builds on (most cited first, 13 of 13)

- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [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)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [SEENN: Towards Temporal Spiking Early-Exit Neural Networks](https://mlsanity.com/paper/2304.01230/) (2023)
- [Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learning](https://mlsanity.com/paper/2109.01905/) (2021)
- [Exploring Temporal Information Dynamics in Spiking Neural Networks](https://mlsanity.com/paper/2211.14406/) (2022)
- [BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons](https://mlsanity.com/paper/2105.13004/) (2021)
- [EventMix: An Efficient Augmentation Strategy for Event-Based Data](https://mlsanity.com/paper/2205.12054/) (2022)

## Built on by (most cited first, 19 of 19)

- [Rethinking Spiking Neural Networks from an Ensemble Learning Perspective](https://mlsanity.com/paper/2502.14218/) (2025)
- [Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networks](https://mlsanity.com/paper/2406.07862/) (2024)
- [VideoA11y: Method and Dataset for Accessible Video Description](https://mlsanity.com/paper/2502.20480/) (2025)
- [Towards Low-latency Event-based Visual Recognition with Hybrid Step-wise Distillation Spiking Neural Networks](https://mlsanity.com/paper/2409.12507/) (2024)
- [Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity](https://mlsanity.com/paper/2506.12087/) (2025)
- [A Double Deep Learning-based Solution for Efficient Event Data Coding and Classification](https://mlsanity.com/paper/2407.15531/) (2024)
- [Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalization](https://mlsanity.com/paper/2408.09108/) (2024)
- [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)
- [NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks](https://mlsanity.com/paper/2406.06305/) (2024)
- [Spike-TBR: a Noise Resilient Neuromorphic Event Representation](https://mlsanity.com/paper/2506.04817/) (2025)
- [Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression](https://mlsanity.com/paper/2407.08744/) (2024)
- [Toward End-to-End Bearing Fault Diagnosis for Industrial Scenarios with Spiking Neural Networks](https://mlsanity.com/paper/2408.11067/) (2024)
- [Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics](https://mlsanity.com/paper/2509.17769/) (2025)
- [NeuCODEX: Edge-Cloud Co-Inference with Spike-Driven Compression and Dynamic Early-Exit](https://mlsanity.com/paper/2509.19156/) (2025)
- [CogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural Networks](https://mlsanity.com/paper/2512.11743/) (2025)
- [Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks](https://mlsanity.com/paper/2603.11676/) (2026)
- [QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition](https://mlsanity.com/paper/2606.07657/) (2026)
- [Noisy group neurons with synchronous resetting for high-performance spiking neural networks](https://mlsanity.com/paper/2608.17394/) (2026)

## Abstract (arXiv)

Neuromorphic object recognition with spiking neural networks (SNNs) is the cornerstone of low-power neuromorphic computing. However, existing SNNs suffer from significant latency, utilizing 10 to 40 timesteps or more, to recognize neuromorphic objects. At low latencies, the performance of existing SNNs is drastically degraded. In this work, we propose the Shrinking SNN (SSNN) to achieve low-latency neuromorphic object recognition without reducing performance. Concretely, we alleviate the temporal redundancy in SNNs by dividing SNNs into multiple stages with progressively shrinking timesteps, which significantly reduces the inference latency. During timestep shrinkage, the temporal transformer smoothly transforms the temporal scale and preserves the information maximally. Moreover, we add multiple early classifiers to the SNN during training to mitigate the mismatch between the surrogate gradient and the true gradient, as well as the gradient vanishing/exploding, thus eliminating the performance degradation at low latency. Extensive experiments on neuromorphic datasets, CIFAR10-DVS, N-Caltech101, and DVS-Gesture have revealed that SSNN is able to improve the baseline accuracy by 6.55% ~ 21.41%. With only 5 average timesteps and without any data augmentation, SSNN is able to achieve an accuracy of 73.63% on CIFAR10-DVS. This work presents a heterogeneous temporal scale SNN and provides valuable insights into the development of high-performance, low-latency SNNs.