# Highly Efficient SNNs for High-speed Object Detection

arXiv: https://arxiv.org/abs/2309.15883 · HTML: https://mlsanity.com/paper/2309.15883/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (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)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers](https://mlsanity.com/paper/1802.00124/) (2018)
- [Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks](https://mlsanity.com/paper/2105.11654/) (2021)
- [Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks](https://mlsanity.com/paper/1809.03142/) (2018)
- [Optical Flow Estimation for Spiking Camera](https://mlsanity.com/paper/2110.03916/) (2021)
- [Exploring Lottery Ticket Hypothesis in Spiking Neural Networks](https://mlsanity.com/paper/2207.01382/) (2022)
- [BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticity](https://mlsanity.com/paper/1711.04214/) (2017)
- [Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation](https://mlsanity.com/paper/2207.02702/) (2022)
- [Efficient Spiking Neural Networks with Radix Encoding](https://mlsanity.com/paper/2105.06943/) (2021)

## Built on by (most cited first, 2 of 2)

- [SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI](https://mlsanity.com/paper/2603.14380/) (2026)
- [Neuromorphic Object Detection: An In-Depth Study and Future Directions](https://mlsanity.com/paper/2607.23576/) (2026)

## Abstract (arXiv)

The high biological properties and low energy consumption of Spiking Neural Networks (SNNs) have brought much attention in recent years. However, the converted SNNs generally need large time steps to achieve satisfactory performance, which will result in high inference latency and computational resources increase. In this work, we propose a highly efficient and fast SNN for object detection. First, we build an initial compact ANN by using quantization training method of convolution layer fold batch normalization layer and neural network modification. Second, we theoretically analyze how to obtain the low complexity SNN correctly. Then, we propose a scale-aware pseudoquantization scheme to guarantee the correctness of the compact ANN to SNN. Third, we propose a continuous inference scheme by using a Feed-Forward Integrate-and-Fire (FewdIF) neuron to realize high-speed object detection. Experimental results show that our efficient SNN can achieve 118X speedup on GPU with only 1.5MB parameters for object detection tasks. We further verify our SNN on FPGA platform and the proposed model can achieve 800+FPS object detection with extremely low latency.