mlsanityData to 7 Oct 2026

Spike-based Neuromorphic Computing for Next-Generation Computer Vision

arXiv 2310.09692 ↗First posted 15 Oct 2023cs.NE cs.AI cs.ETcited by 0

Not on the map. Why?

Abstract (arXiv)

Neuromorphic Computing promises orders of magnitude improvement in energy efficiency compared to traditional von Neumann computing paradigm. The goal is to develop an adaptive, fault-tolerant, low-footprint, fast, low-energy intelligent system by learning and emulating brain functionality which can be realized through innovation in different abstraction layers including material, device, circuit, architecture and algorithm. As the energy consumption in complex vision tasks keep increasing exponentially due to larger data set and resource-constrained edge devices become increasingly ubiquitous, spike-based neuromorphic computing approaches can be viable alternative to deep convolutional neural network that is dominating the vision field today. In this book chapter, we introduce neuromorphic computing, outline a few representative examples from different layers of the design stack (devices, circuits and algorithms) and conclude with a few exciting applications and future research directions that seem promising for computer vision in the near future.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 218 references that are in the map. First posted on arXiv 15 Oct 2023.

Builds on

40 of 218 references.

References · 40

  1. 2019Event-based Vision: A Surveycited by 1,010
  2. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  3. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  4. 2019High Speed and High Dynamic Range Video with an Event Cameracited by 344
  5. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  6. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  7. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 308
  8. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  9. 2018Deep Learning in Spiking Neural Networkscited by 258
  10. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  11. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  12. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
28 more
  1. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
  2. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  3. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  4. 2017Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarioscited by 150
  5. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  6. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  7. 2018Bringing a Blurry Frame Alive at High Frame-Rate with an Event Cameracited by 141
  8. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  9. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  10. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  11. 2022Attention Spiking Neural Networkscited by 103
  12. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  13. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  14. 2017A Survey of Neuromorphic Computing and Neural Networks in Hardwarecited by 82
  15. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  16. 2020Monocular Human Pose Estimation: A Survey of Deep Learning-based Methodscited by 59
  17. 2020LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processingcited by 56
  18. 2017A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)cited by 51
  19. 2015HFirst: A Temporal Approach to Object Recognitioncited by 50
  20. 2016Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardwarecited by 39
  21. 2018Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networkscited by 30
  22. 2018Star Tracking using an Event Cameracited by 30
  23. 2018Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the braincited by 19
  24. 2018Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communicationcited by 14
  25. 2016Training Spiking Deep Networks for Neuromorphic Hardwarecited by 12
  26. 2019ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computingcited by 12
  27. 2023Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environmentcited by 8
  28. 2018Efficient Spiking Neural Networks with Logarithmic Temporal Codingcited by 3

Built on by

Not cited yet.