mlsanityData to 7 Oct 2026

Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes

arXiv 2302.10685 ↗First posted 21 Feb 2023cs.NE cs.AI cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) have attracted great attention due to their distinctive characteristics of low power consumption and temporal information processing. ANN-SNN conversion, as the most commonly used training method for applying SNNs, can ensure that converted SNNs achieve comparable performance to ANNs on large-scale datasets. However, the performance degrades severely under low quantities of time-steps, which hampers the practical applications of SNNs to neuromorphic chips. In this paper, instead of evaluating different conversion errors and then eliminating these errors, we define an offset spike to measure the degree of deviation between actual and desired SNN firing rates. We perform a detailed analysis of offset spike and note that the firing of one additional (or one less) spike is the main cause of conversion errors. Based on this, we propose an optimization strategy based on shifting the initial membrane potential and we theoretically prove the corresponding optimal shifting distance for calibrating the spike. In addition, we also note that our method has a unique iterative property that enables further reduction of conversion errors. The experimental results show that our proposed method achieves state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet datasets. For example, we reach a top-1 accuracy of 67.12% on ImageNet when using 6 time-steps. To the best of our knowledge, this is the first time an ANN-SNN conversion has been shown to simultaneously achieve high accuracy and ultralow latency on complex datasets. Code is available at https://github.com/hzc1208/ANN2SNN_COS.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 21 Feb 2023.

Builds on

28 of 50 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. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  6. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  7. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  8. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  9. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  10. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  11. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  12. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
16 more
  1. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  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. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  7. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  8. 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
  9. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 74
  10. 2019S4NN: temporal backpropagation for spiking neural networks with one spike per neuroncited by 47
  11. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 45
  12. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  13. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  14. 2020Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networkscited by 27
  15. 2020TCL: an ANN-to-SNN Conversion with Trainable Clipping Layerscited by 20
  16. 2017Temporally Efficient Deep Learning with Spikescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 16; 2025: 10; 2026: 4.

38 papers.

Sort:

  1. 2024QKFormer: Hierarchical Spiking Transformer using Q-K Attentioncited by 46
  2. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 36
  3. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  4. 2024SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spikingcited by 29
  5. 2024Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticketcited by 28
  6. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 27
  7. 2024SpikeZIP-TF: Conversion is All You Need for Transformer-based SNNcited by 16
  8. 2023Unleashing the Potential of Spiking Neural Networks by Dynamic Confidencecited by 14
  9. 2024Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networkscited by 14
  10. 2025Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformercited by 13
  11. 2025Quantized Spike-driven Transformercited by 12
  12. 2024LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Modelcited by 10
26 more
  1. 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradientscited by 9
  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. 2023Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagationcited by 8
  5. 2024Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networkscited by 8
  6. 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagationcited by 8
  7. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  8. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  9. 2024SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agentscited by 4
  10. 2024Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalizationcited by 2
  11. 2024Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculationcited by 2
  12. 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deploymentcited by 2
  13. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  14. 2025FAS: Fast ANN-SNN Conversion for Spiking Large Language Modelscited by 1
  15. 2025PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activationcited by 1
  16. 2026Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradientscited by 1
  17. 2023Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkscited by 0
  18. 2023Noise Adaptor in Spiking Neural Networkscited by 0
  19. 2023When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networkscited by 0
  20. 2024Obtaining Optimal Spiking Neural Network in Sequence Learning via CRNN-SNN Conversioncited by 0
  21. 2025DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networkscited by 0
  22. 2025CSDformer: A Conversion Method for Fully Spike-Driven Transformercited by 0
  23. 2025Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Trainingcited by 0
  24. 2026Error Amplification Limits ANN-to-SNN Conversion in Continuous Controlcited by 0
  25. 2026Ge2mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformercited by 0
  26. 2026Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalizationcited by 0