mlsanityData to 7 Oct 2026

Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?

arXiv 2202.03133 ↗First posted 31 Jan 2022cs.NE cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Recent Spiking Neural Networks (SNNs) works focus on an image classification task, therefore various coding techniques have been proposed to convert an image into temporal binary spikes. Among them, rate coding and direct coding are regarded as prospective candidates for building a practical SNN system as they show state-of-the-art performance on large-scale datasets. Despite their usage, there is little attention to comparing these two coding schemes in a fair manner. In this paper, we conduct a comprehensive analysis of the two codings from three perspectives: accuracy, adversarial robustness, and energy-efficiency. First, we compare the performance of two coding techniques with various architectures and datasets. Then, we measure the robustness of the coding techniques on two adversarial attack methods. Finally, we compare the energy-efficiency of two coding schemes on a digital hardware platform. Our results show that direct coding can achieve better accuracy especially for a small number of timesteps. In contrast, rate coding shows better robustness to adversarial attacks owing to the non-differentiable spike generation process. Rate coding also yields higher energy-efficiency than direct coding which requires multi-bit precision for the first layer. Our study explores the characteristics of two codings, which is an important design consideration for building SNNs. The code is made available at https://github.com/Intelligent-Computing-Lab-Yale/Rate-vs-Direct.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

17 of 28 references.

References · 17

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  4. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  5. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  6. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  7. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
  8. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  9. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 119
  10. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  11. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  12. 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
5 more
  1. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 61
  2. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 47
  3. 2019Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagationcited by 43
  4. 2018Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networkscited by 34
  5. 2021Visual Explanations from Spiking Neural Networks using Interspike Intervalscited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 5; 2024: 7; 2025: 7; 2026: 1.

24 papers.

Sort:

By area:

  1. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12
  2. 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradientscited by 9
  3. 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradientscited by 9
  4. 2022Spiking Neural Operators for Scientific Machine Learningcited by 8
  5. 2022SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networkscited by 8
  6. 2023Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networkscited by 7
  7. 2023Adversarially Robust Spiking Neural Networks Through Conversioncited by 7
  8. 2024LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networkscited by 7
  9. 2024ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognitioncited by 3
  10. 2022SIT: A Bionic and Non-Linear Neuron for Spiking Neural Networkcited by 2
  11. 2023SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connectioncited by 2
  12. 2024Robust and Efficient Adversarial Defense in SNNs via Image Purification and Joint Detectioncited by 2
12 more
  1. 2025Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigationcited by 2
  2. 2023Neuroscience inspired scientific machine learning (Part-2): Variable spiking wavelet neural operatorcited by 1
  3. 2024When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-designcited by 1
  4. 2023Asynchronous Bioplausible Neuron for SNN for Event Visioncited by 0
  5. 2024SNNLP: Energy-Efficient Natural Language Processing Using Spiking Neural Networkscited by 0
  6. 2024Topology Optimization of Random Memristors for Input-Aware Dynamic SNNcited by 0
  7. 2025snnTrans-DHZ: A Lightweight Spiking Neural Network Architecture for Underwater Image Dehazingcited by 0
  8. 2025Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithmscited by 0
  9. 2025PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networkscited by 0
  10. 2025Convolutional Spiking-based GRU Cell for Spatio-temporal Datacited by 0
  11. 2025Event-driven physics-informed operator learning for reliability analysiscited by 0
  12. 2026Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networkscited by 0