mlsanityData to 7 Oct 2026

Reducing ANN-SNN Conversion Error through Residual Membrane Potential

arXiv 2302.02091 ↗First posted 4 Feb 2023cs.NE cs.AI cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) have received extensive academic attention due to the unique properties of low power consumption and high-speed computing on neuromorphic chips. Among various training methods of SNNs, ANN-SNN conversion has shown the equivalent level of performance as ANNs on large-scale datasets. However, unevenness error, which refers to the deviation caused by different temporal sequences of spike arrival on activation layers, has not been effectively resolved and seriously suffers the performance of SNNs under the condition of short time-steps. In this paper, we make a detailed analysis of unevenness error and divide it into four categories. We point out that the case of the ANN output being zero while the SNN output being larger than zero accounts for the largest percentage. Based on this, we theoretically prove the sufficient and necessary conditions of this case and propose an optimization strategy based on residual membrane potential to reduce unevenness error. The experimental results show that the proposed method achieves state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet datasets. For example, we reach top-1 accuracy of 64.32% on ImageNet with 10-steps. To the best of our knowledge, this is the first time ANN-SNN conversion can simultaneously achieve high accuracy and ultra-low-latency on the complex dataset. Code is available at https://github.com/hzc1208/ANN2SNNSRP.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 28 of its 56 references that are in the map. First posted on arXiv 4 Feb 2023.

Builds on

28 of 56 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  5. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  6. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  7. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  8. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  9. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  10. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  11. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  12. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
16 more
  1. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  2. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  3. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
  4. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  5. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  6. 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
  7. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 74
  8. 2017Gradient Descent for Spiking Neural Networkscited by 47
  9. 2019S4NN: temporal backpropagation for spiking neural networks with one spike per neuroncited by 47
  10. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 45
  11. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  12. 2016Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networkscited by 31
  13. 2018Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networkscited by 30
  14. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  15. 2020Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networkscited by 27
  16. 2020TCL: an ANN-to-SNN Conversion with Trainable Clipping Layerscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 9; 2025: 15; 2026: 5.

39 papers.

Sort:

By area:

  1. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 163
  2. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  3. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 36
  4. 2023Membrane Potential Batch Normalization for Spiking Neural Networkscited by 35
  5. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  6. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 27
  7. 2023Unleashing the Potential of Spiking Neural Networks by Dynamic Confidencecited by 14
  8. 2024Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networkscited by 14
  9. 2025Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformercited by 13
  10. 2025Quantized Spike-driven Transformercited by 12
  11. 2024Efficient 3D Recognition with Event-driven Spike Sparse Convolutioncited by 11
  12. 2024LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Modelcited by 10
27 more
  1. 2025Towards High-performance Spiking Transformers from ANN to SNN Conversioncited by 10
  2. 2024Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networkscited by 9
  3. 2025Differential Coding for Training-Free ANN-to-SNN Conversioncited by 9
  4. 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagationcited by 8
  5. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  6. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  7. 2024Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Networkcited by 5
  8. 2025Efficient Spiking Point Mamba for Point Cloud Analysiscited by 3
  9. 2024Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculationcited by 2
  10. 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deploymentcited by 2
  11. 2025Efficient ANN-SNN Conversion with Error Compensation Learningcited by 2
  12. 2025New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehiclescited by 2
  13. 2025FAS: Fast ANN-SNN Conversion for Spiking Large Language Modelscited by 1
  14. 2023Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkscited by 0
  15. 2023Noise Adaptor in Spiking Neural Networkscited by 0
  16. 2023When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networkscited by 0
  17. 2025Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neuronscited by 0
  18. 2025DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networkscited by 0
  19. 2025Integer Binary-Range Alignment Neuron for Spiking Neural Networkscited by 0
  20. 2025CSDformer: A Conversion Method for Fully Spike-Driven Transformercited by 0
  21. 2025Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamicscited by 0
  22. 2025Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Trainingcited by 0
  23. 2026Error Amplification Limits ANN-to-SNN Conversion in Continuous Controlcited by 0
  24. 2026QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognitioncited by 0
  25. 2026SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detectioncited by 0
  26. 2026Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalizationcited by 0
  27. 2026Multi-Depth Temporal Fusion for Feedforward, Locally Trained Spiking Neural Networkscited by 0