# Training Robust Spiking Neural Networks on Neuromorphic Data with Spatiotemporal Fragments

arXiv: https://arxiv.org/abs/2207.11659 · HTML: https://mlsanity.com/paper/2207.11659/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 24 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [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)
- [HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification](https://mlsanity.com/paper/1803.07913/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [Neuromorphic Data Augmentation for Training Spiking Neural Networks](https://mlsanity.com/paper/2203.06145/) (2022)
- [DART: Distribution Aware Retinal Transform for Event-based Cameras](https://mlsanity.com/paper/1710.10800/) (2017)
- [AutoSNN: Towards Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2201.12738/) (2022)
- [A Voxel Graph CNN for Object Classification with Event Cameras](https://mlsanity.com/paper/2106.00216/) (2021)
- [EventDrop: data augmentation for event-based learning](https://mlsanity.com/paper/2106.05836/) (2021)
- [Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing](https://mlsanity.com/paper/1910.03579/) (2019)

## Built on by (most cited first, 2 of 2)

- [A Recurrent YOLOv8-based framework for Event-Based Object Detection](https://mlsanity.com/paper/2408.05321/) (2024)
- [Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness](https://mlsanity.com/paper/2503.17394/) (2025)

## Abstract (arXiv)

Neuromorphic vision sensors (event cameras) are inherently suitable for spiking neural networks (SNNs) and provide novel neuromorphic vision data for this biomimetic model. Due to the spatiotemporal characteristics, novel data augmentations are required to process the unconventional visual signals of these cameras. In this paper, we propose a novel Event SpatioTemporal Fragments (ESTF) augmentation method. It preserves the continuity of neuromorphic data by drifting or inverting fragments of the spatiotemporal event stream to simulate the disturbance of brightness variations, leading to more robust spiking neural networks. Extensive experiments are performed on prevailing neuromorphic datasets. It turns out that ESTF provides substantial improvements over pure geometric transformations and outperforms other event data augmentation methods. It is worth noting that the SNNs with ESTF achieve the state-of-the-art accuracy of 83.9% on the CIFAR10-DVS dataset.