# Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks

arXiv: https://arxiv.org/abs/2105.11654 · HTML: https://mlsanity.com/paper/2105.11654/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Spiking Deep Networks with LIF Neurons](https://mlsanity.com/paper/1510.08829/) (2015)
- [Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks](https://mlsanity.com/paper/1612.04052/) (2016)
- [BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticity](https://mlsanity.com/paper/1711.04214/) (2017)
- [Spiking Deep Residual Network](https://mlsanity.com/paper/1805.01352/) (2018)

## Built on by (most cited first, 30 of 78)

- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation](https://mlsanity.com/paper/2304.05627/) (2023)
- [Optimized Potential Initialization for Low-latency Spiking Neural Networks](https://mlsanity.com/paper/2202.01440/) (2022)
- [Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies](https://mlsanity.com/paper/2304.12760/) (2023)
- [Reducing ANN-SNN Conversion Error through Residual Membrane Potential](https://mlsanity.com/paper/2302.02091/) (2023)
- [Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes](https://mlsanity.com/paper/2302.10685/) (2023)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)
- [Spiking PointNet: Spiking Neural Networks for Point Clouds](https://mlsanity.com/paper/2310.06232/) (2023)
- [Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes](https://mlsanity.com/paper/2204.13271/) (2022)
- [Exploring Lottery Ticket Hypothesis in Spiking Neural Networks](https://mlsanity.com/paper/2207.01382/) (2022)
- [Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2110.08858/) (2021)
- [ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks](https://mlsanity.com/paper/2306.03693/) (2023)
- [Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera](https://mlsanity.com/paper/2309.09297/) (2023)
- [Spiking Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2306.17046/) (2023)
- [Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks](https://mlsanity.com/paper/2305.16044/) (2023)
- [SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN](https://mlsanity.com/paper/2406.03470/) (2024)
- [SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation](https://mlsanity.com/paper/2308.15122/) (2023)
- [Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence](https://mlsanity.com/paper/2303.10276/) (2023)
- [Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection](https://mlsanity.com/paper/2306.12010/) (2023)
- [Quantized Spike-driven Transformer](https://mlsanity.com/paper/2501.13492/) (2025)
- [Towards High-performance Spiking Transformers from ANN to SNN Conversion](https://mlsanity.com/paper/2502.21193/) (2025)
- [Meta-learning Spiking Neural Networks with Surrogate Gradient Descent](https://mlsanity.com/paper/2201.10777/) (2022)
- [Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning](https://mlsanity.com/paper/2406.01072/) (2024)
- [A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks](https://mlsanity.com/paper/2206.06129/) (2022)
- [Applications of Spiking Neural Networks in Visual Place Recognition](https://mlsanity.com/paper/2311.13186/) (2023)
- [Spiking SiamFC++: Deep Spiking Neural Network for Object Tracking](https://mlsanity.com/paper/2209.12010/) (2022)
- [Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation](https://mlsanity.com/paper/2410.11488/) (2024)
- [Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration](https://mlsanity.com/paper/2205.10121/) (2022)
- [SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks](https://mlsanity.com/paper/2206.09449/) (2022)

## Abstract (arXiv)

Spiking Neural Networks (SNNs), as bio-inspired energy-efficient neural networks, have attracted great attentions from researchers and industry. The most efficient way to train deep SNNs is through ANN-SNN conversion. However, the conversion usually suffers from accuracy loss and long inference time, which impede the practical application of SNN. In this paper, we theoretically analyze ANN-SNN conversion and derive sufficient conditions of the optimal conversion. To better correlate ANN-SNN and get greater accuracy, we propose Rate Norm Layer to replace the ReLU activation function in source ANN training, enabling direct conversion from a trained ANN to an SNN. Moreover, we propose an optimal fit curve to quantify the fit between the activation value of source ANN and the actual firing rate of target SNN. We show that the inference time can be reduced by optimizing the upper bound of the fit curve in the revised ANN to achieve fast inference. Our theory can explain the existing work on fast reasoning and get better results. The experimental results show that the proposed method achieves near loss less conversion with VGG-16, PreActResNet-18, and deeper structures. Moreover, it can reach 8.6x faster reasoning performance under 0.265x energy consumption of the typical method. The code is available at https://github.com/DingJianhao/OptSNNConvertion-RNL-RIL.