mlsanityData to 14 Oct 2026

Noise Adaptor: Enhancing Low-Latency Spiking Neural Networks through Noise-Injected Low-Bit ANN Conversion

arXiv 2411.17431 ↗First posted 26 Nov 2024cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

We present Noise Adaptor, a novel method for constructing competitive low-latency spiking neural networks (SNNs) by converting noise-injected, low-bit artificial neural networks (ANNs). This approach builds on existing ANN-to-SNN conversion techniques but offers several key improvements: (1) By injecting noise during quantized ANN training, Noise Adaptor better accounts for the dynamic differences between ANNs and SNNs, significantly enhancing SNN accuracy. (2) Unlike previous methods, Noise Adaptor does not require the application of run-time noise correction techniques in SNNs, thereby avoiding modifications to the spiking neuron model and control flow during inference. (3) Our method extends the capability of handling deeper architectures, achieving successful conversions of activation-quantized ResNet-101 and ResNet-152 to SNNs. We demonstrate the effectiveness of our method on CIFAR-10 and ImageNet, achieving competitive performance. The code will be made available as open-source.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 46 references that are in the map. First posted on arXiv 26 Nov 2024.

Builds on

18 of 46 references.

References · 18

  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  2. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  3. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  4. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  5. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
  6. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  7. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 145
  8. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 139
  9. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 122
  10. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 117
  11. 2021Efficient Neuromorphic Signal Processing with Loihi 2cited by 96
  12. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 78
6 more
  1. 2023Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNcited by 46
  2. 2022The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticitycited by 42
  3. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 40
  4. 2023Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networkscited by 18
  5. 2024SpikeZIP-TF: Conversion is All You Need for Transformer-based SNNcited by 18
  6. 2023Unleashing the Potential of Spiking Neural Networks by Dynamic Confidencecited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Noise Adaptor in Spiking Neural Networks
  2. 2024Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications
  3. 2025Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation
  4. 2025Efficient ANN-SNN Conversion with Error Compensation Learning
  5. 2023When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks
  6. 2022Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimator
  7. 2023Spiking Denoising Diffusion Probabilistic Models
  8. 2022tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks