mlsanityData to 14 Oct 2026

Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons

arXiv 2502.14487 ↗First posted 20 Feb 2025cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 100 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

46 of 100 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2020Designing Network Design Spacescited by 960
  5. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  6. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  7. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  8. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  9. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  10. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  11. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 182
  12. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
34 more
  1. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 145
  2. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 139
  3. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 122
  4. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 117
  5. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  6. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  7. 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 88
  8. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 78
  9. 2022Event-based Video Reconstruction via Potential-assisted Spiking Neural Networkcited by 59
  10. 2023SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiationcited by 48
  11. 2023Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNcited by 46
  12. 2022The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticitycited by 42
  13. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 41
  14. 2023SEENN: Towards Temporal Spiking Early-Exit Neural Networkscited by 41
  15. 2023Reducing ANN-SNN Conversion Error through Residual Membrane Potentialcited by 40
  16. 2022Masked Spiking Transformercited by 39
  17. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 38
  18. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  19. 2023SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognitioncited by 30
  20. 2020Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networkscited by 28
  21. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 28
  22. 2023Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networkscited by 26
  23. 2024SpiNNaker2: A Large-Scale Neuromorphic System for Event-Based and Asynchronous Machine Learningcited by 25
  24. 2023Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learningcited by 22
  25. 2020TCL: an ANN-to-SNN Conversion with Trainable Clipping Layerscited by 20
  26. 2023Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognitioncited by 20
  27. 2019DashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object Trackingcited by 19
  28. 2021BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neuronscited by 12
  29. 2017Temporally Efficient Deep Learning with Spikescited by 8
  30. 2023Memory-Efficient Reversible Spiking Neural Networkscited by 6
  31. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  32. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  33. 2021A Design Flow for Mapping Spiking Neural Networks to Many-Core Neuromorphic Hardwarecited by 4
  34. 2021Design of Many-Core Big Little μ Brain for Energy-Efficient Embedded Neuromorphic Computingcited by 2

Built on by

Not cited yet.