mlsanityData to 7 Oct 2026

Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks

arXiv 2312.06372 ↗First posted 11 Dec 2023cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

The Spiking Neural Network (SNN), as one of the biologically inspired neural network infrastructures, has drawn increasing attention recently. It adopts binary spike activations to transmit information, thus the multiplications of activations and weights can be substituted by additions, which brings high energy efficiency. However, in the paper, we theoretically and experimentally prove that the binary spike activation map cannot carry enough information, thus causing information loss and resulting in accuracy decreasing. To handle the problem, we propose a ternary spike neuron to transmit information. The ternary spike neuron can also enjoy the event-driven and multiplication-free operation advantages of the binary spike neuron but will boost the information capacity. Furthermore, we also embed a trainable factor in the ternary spike neuron to learn the suitable spike amplitude, thus our SNN will adopt different spike amplitudes along layers, which can better suit the phenomenon that the membrane potential distributions are different along layers. To retain the efficiency of the vanilla ternary spike, the trainable ternary spike SNN will be converted to a standard one again via a re-parameterization technique in the inference. Extensive experiments with several popular network structures over static and dynamic datasets show that the ternary spike can consistently outperform state-of-the-art methods. Our code is open-sourced at https://github.com/yfguo91/Ternary-Spike.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

33 of 49 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Simple Online and Realtime Trackingcited by 862
  6. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  7. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  8. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  9. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  10. 2018Model compression via distillation and quantizationcited by 287
  11. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  12. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
21 more
  1. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  2. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  3. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  4. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  5. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 143
  6. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  7. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  8. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  9. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  10. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  11. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 70
  12. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 41
  13. 2021Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium Statecited by 39
  14. 2023Reducing ANN-SNN Conversion Error through Residual Membrane Potentialcited by 39
  15. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 38
  16. 2023Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorizationcited by 34
  17. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  18. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  19. 2022Training Spiking Neural Networks with Local Tandem Learningcited by 22
  20. 2020Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemescited by 16
  21. 2022Mesoscopic modeling of hidden spiking neuronscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 18; 2026: 11.

36 papers.

Sort:

By area:

  1. 2024SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanismscited by 31
  2. 2024Learning A Spiking Neural Network for Efficient Image Derainingcited by 16
  3. 2024Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networkscited by 14
  4. 2025Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformercited by 13
  5. 2025Quantized Spike-driven Transformercited by 12
  6. 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspectivecited by 12
  7. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  8. 2025State-Space Model Inspired Multiple-Input Multiple-Output Spiking Neuronscited by 4
  9. 2025Cross Knowledge Distillation between Artificial and Spiking Neural Networkscited by 4
  10. 2024Multi-Bit Mechanism: A Novel Information Transmission Paradigm for Spiking Neural Networkscited by 3
  11. 2024Neuromorphic Wireless Split Computing with Multi-Level Spikescited by 3
  12. 2025Binary Event-Driven Spiking Transformercited by 3
24 more
  1. 2025Improving Performance of Spike-based Deep Q-Learning using Ternary Neuronscited by 3
  2. 2025ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networkscited by 3
  3. 2025SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mambacited by 3
  4. 2024Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalizationcited by 2
  5. 2025Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocationcited by 2
  6. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  7. 2025SpikeDerain: Unveiling Clear Videos from Rainy Sequences Using Color Spike Streamscited by 1
  8. 2026BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learningcited by 1
  9. 2026Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Modelscited by 1
  10. 2026DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditionscited by 1
  11. 2026Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradientscited by 1
  12. 2025Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neuronscited by 0
  13. 2025DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networkscited by 0
  14. 2025Integer Binary-Range Alignment Neuron for Spiking Neural Networkscited by 0
  15. 2025Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamicscited by 0
  16. 2025Discretized Quadratic Integrate-and-Fire Neuron Model for Deep Spiking Neural Networkscited by 0
  17. 2025All in one timestep: Enhancing Sparsity and Energy efficiency in Multi-level Spiking Neural Networkscited by 0
  18. 2026MAR: Efficient Large Language Models via Module-aware Architecture Refinementcited by 0
  19. 2026Ge2mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformercited by 0
  20. 2026Learnable Burst Quantization for Expressive and Efficient Spiking Neural Networkscited by 0
  21. 2026ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantizationcited by 0
  22. 2026SAFformer:Improving Spiking Transformer via Active Predictive Filteringcited by 0
  23. 2026Joint sparse coding and temporal dynamics support context reconfigurationcited by 0
  24. 2026Noisy group neurons with synchronous resetting for high-performance spiking neural networkscited by 0