mlsanityData to 7 Oct 2026

FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversion

arXiv 2403.18388 ↗First posted 27 Mar 2024cs.AI cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) offer a promising avenue for energy-efficient computing compared with Artificial Neural Networks (ANNs), closely mirroring biological neural processes. However, this potential comes with inherent challenges in directly training SNNs through spatio-temporal backpropagation -- stemming from the temporal dynamics of spiking neurons and their discrete signal processing -- which necessitates alternative ways of training, most notably through ANN-SNN conversion. In this work, we introduce a lightweight Forward Temporal Bias Correction (FTBC) technique, aimed at enhancing conversion accuracy without the computational overhead. We ground our method on provided theoretical findings that through proper temporal bias calibration the expected error of ANN-SNN conversion can be reduced to be zero after each time step. We further propose a heuristic algorithm for finding the temporal bias only in the forward pass, thus eliminating the computational burden of backpropagation and we evaluate our method on CIFAR-10/100 and ImageNet datasets, achieving a notable increase in accuracy on all datasets. Codes are released at a GitHub repository.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 72 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

36 of 72 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  4. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  5. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  6. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  7. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  8. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  9. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  10. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
  11. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  12. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 163
24 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. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 116
  5. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  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 82
  8. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 74
  9. 2023SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiationcited by 47
  10. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 41
  11. 2017Deep supervised learning using local errorscited by 41
  12. 2016Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardwarecited by 39
  13. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  14. 2023Reducing ANN-SNN Conversion Error through Residual Membrane Potentialcited by 39
  15. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 38
  16. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 36
  17. 2016Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networkscited by 31
  18. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  19. 2020Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networkscited by 27
  20. 2020TCL: an ANN-to-SNN Conversion with Trainable Clipping Layerscited by 20
  21. 2024Spiker+: a framework for the generation of efficient Spiking Neural Networks FPGA accelerators for inference at the edgecited by 18
  22. 2017Temporally Efficient Deep Learning with Spikescited by 8
  23. 2023Memory-Efficient Reversible Spiking Neural Networkscited by 6
  24. 2018Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2024Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculationcited by 2
  2. 2025PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activationcited by 1
  3. 2025Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neuronscited by 0
  4. 2025SPACT18: Spiking Human Action Recognition Benchmark Dataset with Complementary RGB and Thermal Modalitiescited by 0
  5. 2026Ge2mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformercited by 0