# EventRPG: Event Data Augmentation with Relevance Propagation Guidance

arXiv: https://arxiv.org/abs/2403.09274 · HTML: https://mlsanity.com/paper/2403.09274/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 52 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 30 of 35)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [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)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [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)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks](https://mlsanity.com/paper/2003.06696/) (2020)
- [N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras](https://mlsanity.com/paper/2112.01041/) (2021)
- [EventNeRF: Neural Radiance Fields from a Single Colour Event Camera](https://mlsanity.com/paper/2206.11896/) (2022)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [Event-Based Motion Segmentation by Motion Compensation](https://mlsanity.com/paper/1904.01293/) (2019)
- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation](https://mlsanity.com/paper/2110.07742/) (2021)
- [Event-based Motion Segmentation with Spatio-Temporal Graph Cuts](https://mlsanity.com/paper/2012.08730/) (2020)
- [Event Transformer. A sparse-aware solution for efficient event data processing](https://mlsanity.com/paper/2204.03355/) (2022)
- [Understanding Individual Decisions of CNNs via Contrastive Backpropagation](https://mlsanity.com/paper/1812.02100/) (2018)
- [DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions](https://mlsanity.com/paper/2202.02556/) (2022)
- [ESVIO: Event-based Stereo Visual Inertial Odometry](https://mlsanity.com/paper/2212.13184/) (2022)

## Built on by (most cited first, 7 of 7)

- [A Recurrent YOLOv8-based framework for Event-Based Object Detection](https://mlsanity.com/paper/2408.05321/) (2024)
- [EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision](https://mlsanity.com/paper/2405.18880/) (2024)
- [Learning from Noise: Enhancing DNNs for Event-Based Vision through Controlled Noise Injection](https://mlsanity.com/paper/2506.03918/) (2025)
- [Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients](https://mlsanity.com/paper/2605.27412/) (2026)
- [ShapeAug++: More Realistic Shape Augmentation for Event Data](https://mlsanity.com/paper/2409.11075/) (2024)
- [EventAug: Multifaceted Spatio-Temporal Data Augmentation Methods for Event-based Learning](https://mlsanity.com/paper/2409.11813/) (2024)
- [Hyperdimensional Decoding of Spiking Neural Networks](https://mlsanity.com/paper/2511.08558/) (2025)

## Abstract (arXiv)

Event camera, a novel bio-inspired vision sensor, has drawn a lot of attention for its low latency, low power consumption, and high dynamic range. Currently, overfitting remains a critical problem in event-based classification tasks for Spiking Neural Network (SNN) due to its relatively weak spatial representation capability. Data augmentation is a simple but efficient method to alleviate overfitting and improve the generalization ability of neural networks, and saliency-based augmentation methods are proven to be effective in the image processing field. However, there is no approach available for extracting saliency maps from SNNs. Therefore, for the first time, we present Spiking Layer-Time-wise Relevance Propagation rule (SLTRP) and Spiking Layer-wise Relevance Propagation rule (SLRP) in order for SNN to generate stable and accurate CAMs and saliency maps. Based on this, we propose EventRPG, which leverages relevance propagation on the spiking neural network for more efficient augmentation. Our proposed method has been evaluated on several SNN structures, achieving state-of-the-art performance in object recognition tasks including N-Caltech101, CIFAR10-DVS, with accuracies of 85.62% and 85.55%, as well as action recognition task SL-Animals with an accuracy of 91.59%. Our code is available at https://github.com/myuansun/EventRPG.