# SEENN: Towards Temporal Spiking Early-Exit Neural Networks

arXiv: https://arxiv.org/abs/2304.01230 · HTML: https://mlsanity.com/paper/2304.01230/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 2 Apr 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon](https://mlsanity.com/paper/1705.07565/) (2017)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration](https://mlsanity.com/paper/2106.06984/) (2021)
- [Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratch](https://mlsanity.com/paper/2010.01729/) (2020)
- [Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition](https://mlsanity.com/paper/1509.08971/) (2015)
- [Neural Architecture Search for Spiking Neural Networks](https://mlsanity.com/paper/2201.10355/) (2022)

## Built on by (most cited first, 30 of 41)

- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding](https://mlsanity.com/paper/2404.01174/) (2024)
- [Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Network](https://mlsanity.com/paper/2401.01912/) (2024)
- [Knowing When to Stop: Delay-Adaptive Spiking Neural Network Classifiers with Reliability Guarantees](https://mlsanity.com/paper/2305.11322/) (2023)
- [Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Network](https://mlsanity.com/paper/2412.16219/) (2024)
- [Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity](https://mlsanity.com/paper/2506.12087/) (2025)
- [RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference](https://mlsanity.com/paper/2405.15198/) (2024)
- [Neuronal Competition Groups with Supervised STDP for Spike-Based Classification](https://mlsanity.com/paper/2410.17066/) (2024)
- [Spiking Neural Networks with Dynamic Time Steps for Vision Transformers](https://mlsanity.com/paper/2311.16456/) (2023)
- [Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks](https://mlsanity.com/paper/2407.12516/) (2024)
- [Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Network](https://mlsanity.com/paper/2405.00699/) (2024)
- [AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network](https://mlsanity.com/paper/2408.12293/) (2024)
- [Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment](https://mlsanity.com/paper/2501.15925/) (2025)
- [EvoP: Robust LLM Inference via Evolutionary Pruning](https://mlsanity.com/paper/2502.14910/) (2025)
- [Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness](https://mlsanity.com/paper/2503.17394/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers](https://mlsanity.com/paper/2510.07924/) (2025)
- [When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-design](https://mlsanity.com/paper/2408.12767/) (2024)
- [Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization](https://mlsanity.com/paper/2409.15849/) (2024)
- [PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activation](https://mlsanity.com/paper/2505.01730/) (2025)
- [SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI](https://mlsanity.com/paper/2603.14380/) (2026)
- [Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks](https://mlsanity.com/paper/2311.14265/) (2023)
- [Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression](https://mlsanity.com/paper/2407.08744/) (2024)
- [Topology Optimization of Random Memristors for Input-Aware Dynamic SNN](https://mlsanity.com/paper/2407.18625/) (2024)
- [Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons](https://mlsanity.com/paper/2502.14487/) (2025)
- [Frozen Backpropagation: Relaxing Weight Symmetry in Deep Spiking Neural Networks](https://mlsanity.com/paper/2505.13741/) (2025)
- [Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields](https://mlsanity.com/paper/2507.23033/) (2025)
- [ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference](https://mlsanity.com/paper/2508.01223/) (2025)
- [STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers](https://mlsanity.com/paper/2508.14138/) (2025)
- [SMTrack: End-to-End Trained Spiking Neural Networks for Multi-Object Tracking in RGB Videos](https://mlsanity.com/paper/2508.14607/) (2025)

## 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.