mlsanityData to 7 Oct 2026

SEENN: Towards Temporal Spiking Early-Exit Neural Networks

arXiv 2304.01230 ↗First posted 2 Apr 2023cs.NE cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) have recently become more popular as a biologically plausible substitute for traditional Artificial Neural Networks (ANNs). SNNs are cost-efficient and deployment-friendly because they process input in both spatial and temporal manner using binary spikes. However, we observe that the information capacity in SNNs is affected by the number of timesteps, leading to an accuracy-efficiency tradeoff. In this work, we study a fine-grained adjustment of the number of timesteps in SNNs. Specifically, we treat the number of timesteps as a variable conditioned on different input samples to reduce redundant timesteps for certain data. We call our method Spiking Early-Exit Neural Networks (SEENNs). To determine the appropriate number of timesteps, we propose SEENN-I which uses a confidence score thresholding to filter out the uncertain predictions, and SEENN-II which determines the number of timesteps by reinforcement learning. Moreover, we demonstrate that SEENN is compatible with both the directly trained SNN and the ANN-SNN conversion. By dynamically adjusting the number of timesteps, our SEENN achieves a remarkable reduction in the average number of timesteps during inference. For example, our SEENN-II ResNet-19 can achieve 96.1% accuracy with an average of 1.08 timesteps on the CIFAR-10 test dataset. Code is shared at https://github.com/Intelligent-Computing-Lab-Yale/SEENN.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 33 of its 64 references that are in the map. First posted on arXiv 2 Apr 2023.

Builds on

33 of 64 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  8. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  9. 2021Dynamic Neural Networks: A Surveycited by 405
  10. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  11. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  12. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
21 more
  1. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  2. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  3. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  4. 2018Deep Learning in Spiking Neural Networkscited by 258
  5. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  6. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  7. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  8. 2017Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeoncited by 219
  9. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  10. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 185
  11. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  12. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  13. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
  14. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 116
  15. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  16. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  17. 2015Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognitioncited by 67
  18. 2022Neural Architecture Search for Spiking Neural Networkscited by 52
  19. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  20. 2016Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networkscited by 31
  21. 2022Hoyer regularizer is all you need for ultra low-latency spiking neural networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 12; 2025: 18; 2026: 6.

39 papers.

Sort:

By area:

  1. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 57
  2. 2024SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Groundingcited by 25
  3. 2024Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networkcited by 19
  4. 2023Knowing When to Stop: Delay-Adaptive Spiking Neural Network Classifiers with Reliability Guaranteescited by 8
  5. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  6. 2024RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inferencecited by 4
  7. 2024Neuronal Competition Groups with Supervised STDP for Spike-Based Classificationcited by 4
  8. 2025Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexitycited by 4
  9. 2023Spiking Neural Networks with Dynamic Time Steps for Vision Transformerscited by 3
  10. 2024Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Networkcited by 2
  11. 2024Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networkscited by 2
  12. 2024AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Networkcited by 2
27 more
  1. 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deploymentcited by 2
  2. 2025EvoP: Robust LLM Inference via Evolutionary Pruningcited by 2
  3. 2025Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendlinesscited by 2
  4. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  5. 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillerscited by 2
  6. 2024When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-designcited by 1
  7. 2025PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activationcited by 1
  8. 2026SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AIcited by 1
  9. 2023Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkscited by 0
  10. 2024Toward Efficient Deep Spiking Neuron Networks:A Survey On Compressioncited by 0
  11. 2024Topology Optimization of Random Memristors for Input-Aware Dynamic SNNcited by 0
  12. 2025Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neuronscited by 0
  13. 2025Frozen Backpropagation: Relaxing Weight Symmetry in Deep Spiking Neural Networkscited by 0
  14. 2025Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fieldscited by 0
  15. 2025ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inferencecited by 0
  16. 2025STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformerscited by 0
  17. 2025SMTrack: End-to-End Trained Spiking Neural Networks for Multi-Object Tracking in RGB Videoscited by 0
  18. 2025NeuCODEX: Edge-Cloud Co-Inference with Spike-Driven Compression and Dynamic Early-Exitcited by 0
  19. 2025Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Trainingcited by 0
  20. 2025A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networkscited by 0
  21. 2025A Closer Look at Knowledge Distillation in Spiking Neural Network Trainingcited by 0
  22. 2025Hyperdimensional Decoding of Spiking Neural Networkscited by 0
  23. 2026BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuroncited by 0
  24. 2026Detecting AI-Generated Videos with Spiking Neural Networkscited by 0
  25. 2026ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computingcited by 0
  26. 2026Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exitcited by 0
  27. 2026BLADE: ReliaBle Dynamic Hardware-Aware SNN-ANN Boundary SeLection for Event-BAseD Object DEtectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes
  2. 2025Delays in Spiking Neural Networks: A State Space Model Approach
  3. 2024Spiking Diffusion Models
  4. 2024SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models
  5. 2024Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks
  6. 2023Spiking Denoising Diffusion Probabilistic Models
  7. 2026Parallel Training in Spiking Neural Networks
  8. 2024P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks