Spiking Neural Networks, as a third-generation neural network, are well-suited for edge AI applications due to their binary spike nature. However, when it comes to complex tasks like object detection, SNNs often require a substantial number of time steps to achieve high performance. This limitation significantly hampers the widespread adoption of SNNs in latency-sensitive edge devices. In this paper, our focus is on generating highly accurate and low-latency SNNs specifically for object detection. Firstly, we systematically derive the conversion between SNNs and ANNs and analyze how to improve the consistency between them: improving the spike firing rate and reducing the quantization error. Then we propose a structural replacement, quantization of ANN activation and residual fix to allevicate the disparity. We evaluate our method on challenging dataset MS COCO, PASCAL VOC and our spike dataset. The experimental results show that the proposed method achieves higher accuracy and lower latency compared to previous work Spiking-YOLO. The advantages of SNNs processing of spike signals are also demonstrated.

翻译：脉冲神经网络作为第三代神经网络，因其二进制脉冲特性而非常适合边缘人工智能应用。然而，在目标检测等复杂任务中，SNN通常需要大量时间步才能达到高性能。这一限制严重阻碍了SNN在延迟敏感的边缘设备中的广泛应用。本文专注于生成专门用于目标检测的高精度低延迟SNN。首先，我们系统推导了SNN与ANN之间的转换，并分析了如何改善二者的一致性：提高脉冲发放率并降低量化误差。随后，我们提出结构替换、ANN激活值量化与残差修正方法来缓解差异。我们在具有挑战性的数据集MS COCO、PASCAL VOC以及自建脉冲数据集上评估了该方法。实验结果表明，与先前工作Spiking-YOLO相比，所提方法实现了更高精度和更低延迟。同时，SNN处理脉冲信号的优势也得到了验证。