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

Source: [Noise Adaptor: Enhancing Low-Latency Spiking Neural Networks through Noise-Injected Low-Bit ANN Conversion](<https://www.sota2.com/research/paper/68fa75e41e209131cea6a7f0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:43:37.123Z

Authors: Chen Li, Bipin.Rajendran

Published: 2024-11-26T13:39:52.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.17431>)

[PDF](<https://arxiv.org/pdf/2411.17431.pdf>)