# Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization

arXiv: https://arxiv.org/abs/2205.07473 · HTML: https://mlsanity.com/paper/2205.07473/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2022.

## Built on by (most cited first, 14 of 14)

- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks](https://mlsanity.com/paper/2206.10177/) (2022)
- [EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2403.12574/) (2024)
- [LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model](https://mlsanity.com/paper/2402.00411/) (2024)
- [Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity](https://mlsanity.com/paper/2506.12087/) (2025)
- [Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model](https://mlsanity.com/paper/2410.15689/) (2024)
- [FAS: Fast ANN-SNN Conversion for Spiking Large Language Models](https://mlsanity.com/paper/2502.04405/) (2025)
- [Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning](https://mlsanity.com/paper/2510.04098/) (2025)
- [When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks](https://mlsanity.com/paper/2312.06900/) (2023)
- [DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks](https://mlsanity.com/paper/2503.10052/) (2025)
- [A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks](https://mlsanity.com/paper/2508.12609/) (2025)
- [Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping](https://mlsanity.com/paper/2508.14520/) (2025)
- [CSDformer: A Conversion Method for Fully Spike-Driven Transformer](https://mlsanity.com/paper/2509.17461/) (2025)
- [Batch Normalization-Free Fully Integer Quantized Neural Networks via Progressive Tandem Learning](https://mlsanity.com/paper/2512.16476/) (2025)

## Abstract (arXiv)

Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under a few time steps, which restricts the applications of SNN on latency-sensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the state-of-the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://github.com/Windere/snn-cvt-dual-phase.