# Rethinking Pretraining as a Bridge from ANNs to SNNs

arXiv: https://arxiv.org/abs/2203.01158 · HTML: https://mlsanity.com/paper/2203.01158/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [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)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Graph-Based Object Classification for Neuromorphic Vision Sensing](https://mlsanity.com/paper/1908.06648/) (2019)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [Exploring the Connection Between Binary and Spiking Neural Networks](https://mlsanity.com/paper/2002.10064/) (2020)
- [ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks](https://mlsanity.com/paper/2110.12211/) (2021)
- [Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication](https://mlsanity.com/paper/1810.11521/) (2018)

## Built on by (most cited first, 4 of 4)

- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks](https://mlsanity.com/paper/2206.06129/) (2022)
- [MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition](https://mlsanity.com/paper/2404.10210/) (2024)

## Abstract (arXiv)

Spiking neural networks (SNNs) are known as a typical kind of brain-inspired models with their unique features of rich neuronal dynamics, diverse coding schemes and low power consumption properties. How to obtain a high-accuracy model has always been the main challenge in the field of SNN. Currently, there are two mainstream methods, i.e., obtaining a converted SNN through converting a well-trained Artificial Neural Network (ANN) to its SNN counterpart or training an SNN directly. However, the inference time of a converted SNN is too long, while SNN training is generally very costly and inefficient. In this work, a new SNN training paradigm is proposed by combining the concepts of the two different training methods with the help of the pretrain technique and BP-based deep SNN training mechanism. We believe that the proposed paradigm is a more efficient pipeline for training SNNs. The pipeline includes pipeS for static data transfer tasks and pipeD for dynamic data transfer tasks. SOTA results are obtained in a large-scale event-driven dataset ES-ImageNet. For training acceleration, we achieve the same (or higher) best accuracy as similar LIF-SNNs using 1/10 training time on ImageNet-1K and 2/5 training time on ES-ImageNet and also provide a time-accuracy benchmark for a new dataset ES-UCF101. These experimental results reveal the similarity of the functions of parameters between ANNs and SNNs and also demonstrate the various potential applications of this SNN training pipeline.