# Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection

arXiv: https://arxiv.org/abs/2306.12010 · HTML: https://mlsanity.com/paper/2306.12010/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 67 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Efficient Neuromorphic Signal Processing with Loihi 2](https://mlsanity.com/paper/2111.03746/) (2021)
- [Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks](https://mlsanity.com/paper/2105.11654/) (2021)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [Optimized Potential Initialization for Low-latency Spiking Neural Networks](https://mlsanity.com/paper/2202.01440/) (2022)
- [A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/2104.10719/) (2021)
- [Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes](https://mlsanity.com/paper/2204.13271/) (2022)
- [A Spiking Neural Network for Image Segmentation](https://mlsanity.com/paper/2106.08921/) (2021)
- [Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks](https://mlsanity.com/paper/2210.06386/) (2022)
- [Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes](https://mlsanity.com/paper/2005.03231/) (2020)
- [Tuning Convolutional Spiking Neural Network with Biologically-plausible Reward Propagation](https://mlsanity.com/paper/2010.04434/) (2020)
- [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)
- [SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking](https://mlsanity.com/paper/2003.07584/) (2020)
- [Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks](https://mlsanity.com/paper/2205.02115/) (2022)
- [Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integration](https://mlsanity.com/paper/2202.06821/) (2022)
- [Optimizing the Consumption of Spiking Neural Networks with Activity Regularization](https://mlsanity.com/paper/2204.01460/) (2022)
- [Hardware Implementation of Spiking Neural Networks Using Time-To-First-Spike Encoding](https://mlsanity.com/paper/2006.05033/) (2020)
- [Spiking Approximations of the MaxPooling Operation in Deep SNNs](https://mlsanity.com/paper/2205.07076/) (2022)

## Built on by (most cited first, 15 of 15)

- [Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer](https://mlsanity.com/paper/2503.00226/) (2025)
- [Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion](https://mlsanity.com/paper/2405.17903/) (2024)
- [Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection](https://mlsanity.com/paper/2402.01287/) (2024)
- [Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation](https://mlsanity.com/paper/2510.00681/) (2025)
- [Fully Spiking Neural Networks for Unified Frame-Event Object Tracking](https://mlsanity.com/paper/2505.20834/) (2025)
- [Deep Multi-Threshold Spiking-UNet for Image Processing](https://mlsanity.com/paper/2307.10974/) (2023)
- [Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model](https://mlsanity.com/paper/2410.15689/) (2024)
- [Neuromorphic Wireless Split Computing with Multi-Level Spikes](https://mlsanity.com/paper/2411.04728/) (2024)
- [Spike Accumulation Forwarding for Effective Training of Spiking Neural Networks](https://mlsanity.com/paper/2310.02772/) (2023)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning](https://mlsanity.com/paper/2510.04098/) (2025)
- [TSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit](https://mlsanity.com/paper/2404.00855/) (2024)
- [Temporal Dynamics Enhancer for Directly Trained Spiking Object Detectors](https://mlsanity.com/paper/2512.02447/) (2025)
- [Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks](https://mlsanity.com/paper/2605.25293/) (2026)
- [SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts](https://mlsanity.com/paper/2610.15745/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have garnered widespread interest for their energy efficiency and brain-inspired event-driven properties. While recent methods like Spiking-YOLO have expanded the SNNs to more challenging object detection tasks, they often suffer from high latency and low detection accuracy, making them difficult to deploy on latency sensitive mobile platforms. Furthermore, the conversion method from Artificial Neural Networks (ANNs) to SNNs is hard to maintain the complete structure of the ANNs, resulting in poor feature representation and high conversion errors. To address these challenges, we propose two methods: timesteps compression and spike-time-dependent integrated (STDI) coding. The former reduces the timesteps required in ANN-SNN conversion by compressing information, while the latter sets a time-varying threshold to expand the information holding capacity. We also present a SNN-based ultra-low latency and high accurate object detection model (SUHD) that achieves state-of-the-art performance on nontrivial datasets like PASCAL VOC and MS COCO, with about remarkable 750x fewer timesteps and 30% mean average precision (mAP) improvement, compared to the Spiking-YOLO on MS COCO datasets. To the best of our knowledge, SUHD is the deepest spike-based object detection model to date that achieves ultra low timesteps to complete the lossless conversion.