Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN
Top Cited Papers
- 18 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14546-14562
Abstract
Spiking neural networks (SNNs) have shown advantages in computation and energy efficiency over traditional artificial neural networks (ANNs) thanks to their event-driven representations. SNNs also replace weight multiplications in ANNs with additions, which are more energy-efficient and less computationally intensive. However, it remains a challenge to train deep SNNs due to the discrete spiking function. A popular approach to circumvent this challenge is ANN-to-SNN conversion. However, due to the quantization error and accumulating error, it often requires lots of time steps (high inference latency) to achieve high performance, which negates SNN's advantages. To this end, this paper proposes Fast-SNN that achieves high performance with low latency. We demonstrate the equivalent mapping between temporal quantization in SNNs and spatial quantization in ANNs, based on which the minimization of the quantization error is transferred to quantized ANN training. With the minimization of the quantization error, we show that the sequential error is the primary cause of the accumulating error, which is addressed by introducing a signed IF neuron model and a layer-wise fine-tuning mechanism. Our method achieves state-of-the-art performance and low latency on various computer vision tasks, including image classification, object detection, and semantic segmentation. Codes are available at: https://github.com/yangfan-hu/Fast-SNN .Keywords
All Related Versions
Funding Information
- STI 2030 Major Projects (2021ZD0200400)
- National Natural Science Foundation of China (61925603, 62376247, U1909202)
- Key Research and Development Program of Zhejiang Province in China (2020C03004)
- Zhejiang Lab (2021KC0AC01)
This publication has 54 references indexed in Scilit:
- Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing2015
- Fully convolutional networks for semantic segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Spiking Deep Convolutional Neural Networks for Energy-Efficient Object RecognitionInternational Journal of Computer Vision, 2014
- A million spiking-neuron integrated circuit with a scalable communication network and interfaceScience, 2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate Coding and Coincidence Processing--Application to Feedforward ConvNetsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997