mlsanityData to 14 Oct 2026

TS-SNN: Temporal Shift Module for Spiking Neural Networks

arXiv 2505.04165 ↗First posted 7 May 2025cs.NE cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) are increasingly recognized for their biological plausibility and energy efficiency, positioning them as strong alternatives to Artificial Neural Networks (ANNs) in neuromorphic computing applications. SNNs inherently process temporal information by leveraging the precise timing of spikes, but balancing temporal feature utilization with low energy consumption remains a challenge. In this work, we introduce Temporal Shift module for Spiking Neural Networks (TS-SNN), which incorporates a novel Temporal Shift (TS) module to integrate past, present, and future spike features within a single timestep via a simple yet effective shift operation. A residual combination method prevents information loss by integrating shifted and original features. The TS module is lightweight, requiring only one additional learnable parameter, and can be seamlessly integrated into existing architectures with minimal additional computational cost. TS-SNN achieves state-of-the-art performance on benchmarks like CIFAR-10 (96.72%), CIFAR-100 (80.28%), and ImageNet (70.61%) with fewer timesteps, while maintaining low energy consumption. This work marks a significant step forward in developing efficient and accurate SNN architectures.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 61 references that are in the map. First posted on arXiv 7 May 2025.

Builds on

34 of 61 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
  4. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  5. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  6. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  7. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  8. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  9. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  10. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  11. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  12. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 123
22 more
  1. 2022Attention Spiking Neural Networkscited by 107
  2. 2017Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutionscited by 93
  3. 2021S2-MLP: Spatial-Shift MLP Architecture for Visioncited by 83
  4. 2021Advancing Spiking Neural Networks towards Deep Residual Learningcited by 79
  5. 2022A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shiftcited by 68
  6. 2021ACTION-Net: Multipath Excitation for Action Recognitioncited by 63
  7. 2022GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 63
  8. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 44
  9. 2019All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classificationcited by 38
  10. 2023Membrane Potential Batch Normalization for Spiking Neural Networkscited by 35
  11. 2021A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detectioncited by 31
  12. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 28
  13. 2023Training Full Spike Neural Networks via Auxiliary Accumulation Pathwaycited by 26
  14. 2018Constructing Fast Network through Deconstruction of Convolutioncited by 24
  15. 2022Real Spike: Learning Real-valued Spikes for Spiking Neural Networkscited by 22
  16. 2022Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Networkcited by 19
  17. 2019Minimal Solutions for Relative Pose with a Single Affine Correspondencecited by 12
  18. 2023Biologically inspired structure learning with reverse knowledge distillation for spiking neural networkscited by 11
  19. 2025STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networkscited by 11
  20. 2024FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networkscited by 10
  21. 2025Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networkscited by 10
  22. 2023Tensor Decomposition Based Attention Module for Spiking Neural Networkscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026PTS-SNN: A Prompt-Tuned Temporal Shift Spiking Neural Networks for Efficient Speech Emotion Recognitioncited by 1
  2. 2025Spiking Vocos: An Energy-Efficient Neural Vocodercited by 0
  3. 2026Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networkscited by 0
  4. 2026QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognitioncited by 0
  5. 2026RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Visioncited by 0