Low Latency of object detection for spikng neural network
This addresses the limitation of SNNs for latency-sensitive edge devices, though it appears incremental as it builds on existing conversion techniques.
The paper tackles the problem of high latency in Spiking Neural Networks (SNNs) for object detection by proposing a method to improve conversion from ANNs, achieving higher accuracy and lower latency than prior work like Spiking-YOLO on datasets such as MS COCO and PASCAL VOC.
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.