mlsanityData to 14 Oct 2026

Hoyer regularizer is all you need for ultra low-latency spiking neural networks

arXiv 2212.10170 ↗First posted 20 Dec 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Spiking Neural networks (SNN) have emerged as an attractive spatio-temporal computing paradigm for a wide range of low-power vision tasks. However, state-of-the-art (SOTA) SNN models either incur multiple time steps which hinder their deployment in real-time use cases or increase the training complexity significantly. To mitigate this concern, we present a training framework (from scratch) for one-time-step SNNs that uses a novel variant of the recently proposed Hoyer regularizer. We estimate the threshold of each SNN layer as the Hoyer extremum of a clipped version of its activation map, where the clipping threshold is trained using gradient descent with our Hoyer regularizer. This approach not only downscales the value of the trainable threshold, thereby emitting a large number of spikes for weight update with a limited number of iterations (due to only one time step) but also shifts the membrane potential values away from the threshold, thereby mitigating the effect of noise that can degrade the SNN accuracy. Our approach outperforms existing spiking, binary, and adder neural networks in terms of the accuracy-FLOPs trade-off for complex image recognition tasks. Downstream experiments on object detection also demonstrate the efficacy of our approach.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 46 of its 73 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

46 of 73 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  7. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  8. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  9. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  10. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  11. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  12. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
34 more
  1. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  2. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 205
  3. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  4. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 184
  5. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 177
  6. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 144
  7. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 139
  8. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 117
  9. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 100
  10. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  11. 2019AdderNet: Do We Really Need Multiplications in Deep Learning?cited by 82
  12. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 80
  13. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 71
  14. 2019DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measurescited by 56
  15. 2021Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Networkcited by 55
  16. 2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 55
  17. 2022Neural Architecture Search for Spiking Neural Networkscited by 53
  18. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  19. 2019Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagationcited by 45
  20. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 41
  21. 2016Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardwarecited by 40
  22. 2020BiDet: An Efficient Binarized Object Detectorcited by 33
  23. 2022Exploring Lottery Ticket Hypothesis in Spiking Neural Networkscited by 26
  24. 2022SATA: Sparsity-Aware Training Accelerator for Spiking Neural Networkscited by 20
  25. 2021One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latencycited by 17
  26. 2022P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applicationscited by 16
  27. 2021Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encodingcited by 10
  28. 2021Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks?cited by 9
  29. 2016Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognitioncited by 7
  30. 2021Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compressioncited by 7
  31. 2022P2M-DeTrack: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Trackingcited by 6
  32. 2021Winograd Algorithm for AdderNetcited by 4
  33. 2022Toward Efficient Hyperspectral Image Processing inside Camera Pixelscited by 4
  34. 2020Always-On, Sub-300-nW, Event-Driven Spiking Neural Network based on Spike-Driven Clock-Generation and Clock- and Power-Gating for an Ultra-Low-Power Intelligent Devicecited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3.

4 papers.

  1. 2023SEENN: Towards Temporal Spiking Early-Exit Neural Networkscited by 41
  2. 2022In-Sensor & Neuromorphic Computing are all you need for Energy Efficient Computer Visioncited by 6
  3. 2023Spiking Neural Networks with Dynamic Time Steps for Vision Transformerscited by 3
  4. 2023When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networkscited by 0