mlsanityData to 7 Oct 2026

Neuromorphic Data Augmentation for Training Spiking Neural Networks

arXiv 2203.06145 ↗First posted 11 Mar 2022cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Developing neuromorphic intelligence on event-based datasets with Spiking Neural Networks (SNNs) has recently attracted much research attention. However, the limited size of event-based datasets makes SNNs prone to overfitting and unstable convergence. This issue remains unexplored by previous academic works. In an effort to minimize this generalization gap, we propose Neuromorphic Data Augmentation (NDA), a family of geometric augmentations specifically designed for event-based datasets with the goal of significantly stabilizing the SNN training and reducing the generalization gap between training and test performance. The proposed method is simple and compatible with existing SNN training pipelines. Using the proposed augmentation, for the first time, we demonstrate the feasibility of unsupervised contrastive learning for SNNs. We conduct comprehensive experiments on prevailing neuromorphic vision benchmarks and show that NDA yields substantial improvements over previous state-of-the-art results. For example, the NDA-based SNN achieves accuracy gain on CIFAR10-DVS and N-Caltech 101 by 10.1% and 13.7%, respectively. Code is available on GitHub https://github.com/Intelligent-Computing-Lab-Yale/NDA_SNN

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 51 of its 75 references that are in the map. First posted on arXiv 11 Mar 2022.

Builds on

51 of 75 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
38 more
  1. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2017Random Erasing Data Augmentationcited by 1,235
  8. 2019Event-based Vision: A Surveycited by 1,010
  9. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  10. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  11. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  12. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  13. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 308
  14. 2019PyHessian: Neural Networks Through the Lens of the Hessiancited by 291
  15. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  16. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  17. 2019Fast AutoAugmentcited by 243
  18. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  19. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 215
  20. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
  21. 2017Neural Style Transfer: A Reviewcited by 199
  22. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  23. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  24. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  25. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
  26. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  27. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  28. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 70
  29. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  30. 2020LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processingcited by 56
  31. 2018BindsNET: A machine learning-oriented spiking neural networks library in Pythoncited by 42
  32. 2016Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardwarecited by 39
  33. 2017DART: Distribution Aware Retinal Transform for Event-based Camerascited by 39
  34. 2016Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networkscited by 31
  35. 2020MixMix: All You Need for Data-Free Compression Are Feature and Data Mixingcited by 29
  36. 2021EventDrop: data augmentation for event-based learningcited by 28
  37. 2021CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processorcited by 27
  38. 2021ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networkscited by 24

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 11; 2024: 16; 2025: 9; 2026: 8.

52 papers.

Sort:

  1. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
  2. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 163
  3. 2024SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networkscited by 38
  4. 2023Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networkscited by 37
  5. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 33
  6. 2024Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Modelscited by 31
  7. 2024Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticketcited by 28
  8. 2022Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Networkcited by 19
  9. 2022Spiking Neural Networks for Frame-based and Event-based Single Object Localizationcited by 18
  10. 2023Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioningcited by 14
  11. 2024EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classificationcited by 13
  12. 2023Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradientcited by 11
38 more
  1. 2023Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Futurecited by 10
  2. 2023Spiking-Fer: Spiking Neural Network for Facial Expression Recognition With Event Camerascited by 10
  3. 2024A Recurrent YOLOv8-based framework for Event-Based Object Detectioncited by 9
  4. 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradientscited by 9
  5. 2024ShapeAug: Occlusion Augmentation for Event Camera Datacited by 6
  6. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  7. 2022Hoyer regularizer is all you need for ultra low-latency spiking neural networkscited by 4
  8. 2023NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNNcited by 4
  9. 2025Cross Knowledge Distillation between Artificial and Spiking Neural Networkscited by 4
  10. 2023Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural networks: from Algorithms to Technologycited by 3
  11. 2024Membership Privacy Evaluation in Deep Spiking Neural Networkscited by 3
  12. 2022Training Robust Spiking Neural Networks on Neuromorphic Data with Spatiotemporal Fragmentscited by 2
  13. 2023Attention-free Spikformer: Mixing Spike Sequences with Simple Linear Transformscited by 2
  14. 2024Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Networkcited by 2
  15. 2024EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Visioncited by 2
  16. 2024Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalizationcited by 2
  17. 2025Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Camerascited by 2
  18. 2025Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domaincited by 2
  19. 2026Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognitioncited by 2
  20. 2022Event Transformercited by 1
  21. 2023Training Robust Spiking Neural Networks with ViewPoint Transform and SpatioTemporal Stretchingcited by 1
  22. 2024When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-designcited by 1
  23. 2024DS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attentioncited by 1
  24. 2025Regularization-based Framework for Quantization-, Fault- and Variability-Aware Trainingcited by 1
  25. 2025Learning from Noise: Enhancing DNNs for Event-Based Vision through Controlled Noise Injectioncited by 1
  26. 2025Spike-TBR: a Noise Resilient Neuromorphic Event Representationcited by 1
  27. 2025Benchmarking Microsaccade Recognition with Event Cameras: A Novel Dataset and Evaluationcited by 1
  28. 2026BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learningcited by 1
  29. 2026Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradientscited by 1
  30. 2022Training Stronger Spiking Neural Networks with Biomimetic Adaptive Internal Association Neuronscited by 0
  31. 2023Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkscited by 0
  32. 2024Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptationcited by 0
  33. 2024Fourier or Wavelet bases as counterpart self-attention in spikformer for efficient visual classificationcited by 0
  34. 2024ShapeAug++: More Realistic Shape Augmentation for Event Datacited by 0
  35. 2025Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domaincited by 0
  36. 2026Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, Generalcited by 0
  37. 2026Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networkscited by 0
  38. 2026SpikeCLR: Contrastive Self-Supervised Learning for Few-Shot Event-Based Vision using Spiking Neural Networkscited by 0

50 most cited of 52 All 52 (JSON)