mlsanityData to 14 Oct 2026

Sparse Compressed Spiking Neural Network Accelerator for Object Detection

arXiv 2205.00778 ↗First posted 2 May 2022cs.AR cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks (SNNs), which are inspired by the human brain, have recently gained popularity due to their relatively simple and low-power hardware for transmitting binary spikes and highly sparse activation maps. However, because SNNs contain extra time dimension information, the SNN accelerator will require more buffers and take longer to infer, especially for the more difficult high-resolution object detection task. As a result, this paper proposes a sparse compressed spiking neural network accelerator that takes advantage of the high sparsity of activation maps and weights by utilizing the proposed gated one-to-all product for low power and highly parallel model execution. The experimental result of the neural network shows 71.5% mAP with mixed (1,3) time steps on the IVS 3cls dataset. The accelerator with the TSMC 28nm CMOS process can achieve 1024×576@29 frames per second processing when running at 500MHz with 35.88TOPS/W energy efficiency and 1.05mJ energy consumption per frame.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 13 of its 35 references that are in the map. First posted on arXiv 2 May 2022.

Builds on

13 of 35 references.

References · 13

  1. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  3. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  4. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  5. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  6. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 177
  7. 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 135
  8. 2017A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)cited by 52
  9. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 46
  10. 2019Comprehensive SNN Compression Using ADMM Optimization and Activity Regularizationcited by 45
  11. 2021Pruning of Deep Spiking Neural Networks through Gradient Rewiringcited by 43
  12. 2021Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks?cited by 9
1 more
  1. 2017Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activationscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 0; 2025: 2.

6 papers.

  1. 2022Attention Spiking Neural Networkscited by 107
  2. 2023Deep Directly-Trained Spiking Neural Networks for Object Detectioncited by 77
  3. 2022Energy-Efficient Deployment of Machine Learning Workloads on Neuromorphic Hardwarecited by 3
  4. 2023MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networkscited by 3
  5. 2025A 71.2-μW Speech Recognition Accelerator with Recurrent Spiking Neural Networkcited by 1
  6. 2025SpikeX: Exploring Accelerator Architecture and Network-Hardware Co-Optimization for Sparse Spiking Neural Networkscited by 1