mlsanityData to 14 Oct 2026

Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks

arXiv 2603.11676 ↗First posted 12 Mar 2026cs.NE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal pattern capture capabilities, they also incur inherent inconsistencies that severely compromise representation. In this paper, we perform dual consistency optimization via Stable Spike to mitigate this problem, thereby improving the recognition performance of SNNs. With the hardware-friendly ``AND" bit operation, we efficiently decouple the stable spike skeleton from the multi-timestep spike maps, thereby capturing critical semantics while reducing inconsistencies from variable noise spikes. Enforcing the unstable spike maps to converge to the stable spike skeleton significantly improves the inherent consistency across timesteps. Furthermore, we inject amplitude-aware spike noise into the stable spike skeleton to diversify the representations while preserving consistent semantics. The SNN is encouraged to produce perturbation-consistent predictions, thereby contributing to generalization. Extensive experiments across multiple architectures and datasets validate the effectiveness and versatility of our method. In particular, our method significantly advances neuromorphic object recognition under ultra-low latency, improving accuracy by up to 8.33%. This will help unlock the full power consumption and speed potential of SNNs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

36 of 58 references.

References · 36

  1. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  2. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  3. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
  4. 2023Spike-driven Transformercited by 146
  5. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  6. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  7. 2023Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipelinecited by 52
  8. 2024QKFormer: Hierarchical Spiking Transformer using Q-K Attentioncited by 49
  9. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 48
  10. 2020Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networkscited by 47
  11. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 44
  12. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
24 more
  1. 2024SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networkscited by 40
  2. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 35
  3. 2021Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learningcited by 27
  4. 2022Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?cited by 25
  5. 2023Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learningcited by 22
  6. 2024CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 21
  7. 2025Spiking Vision Transformer with Saccadic Attentioncited by 21
  8. 2024Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networkcited by 19
  9. 2024Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networkscited by 14
  10. 2024TIM: An Efficient Temporal Interaction Module for Spiking Transformercited by 12
  11. 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspectivecited by 12
  12. 2024Spiking Wavelet Transformercited by 11
  13. 2024BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge Distillationcited by 11
  14. 2025STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networkscited by 11
  15. 2023Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Futurecited by 10
  16. 2024FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networkscited by 10
  17. 2023An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domaincited by 9
  18. 2024Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networkscited by 9
  19. 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagationcited by 8
  20. 2025TS-SNN: Temporal Shift Module for Spiking Neural Networkscited by 5
  21. 2022Flash-Cosmos: In-Flash Bulk Bitwise Operations Using Inherent Computation Capability of NAND Flash Memorycited by 3
  22. 2023Temporal Contrastive Learning for Spiking Neural Networkscited by 3
  23. 2025ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networkscited by 3
  24. 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillerscited by 2

Built on by

Not cited yet.