U-Net, known for its simple yet efficient architecture, is widely utilized
for image processing tasks and is particularly suitable for deployment on
neuromorphic chips. This paper introduces the novel concept of Spiking-UNet for
image processing, which combines the power of Spiking Neural Networks (SNNs)
with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two
primary challenges: ensuring high-fidelity information propagation through the
network via spikes and formulating an effective training strategy. To address
the issue of information loss, we introduce multi-threshold spiking neurons,
which improve the efficiency of information transmission within the
Spiking-UNet. For the training strategy, we adopt a conversion and fine-tuning
pipeline that leverage pre-trained U-Net models. During the conversion process,
significant variability in data distribution across different parts is observed
when utilizing skip connections. Therefore, we propose a connection-wise
normalization method to prevent inaccurate firing rates. Furthermore, we adopt
a flow-based training method to fine-tune the converted models, reducing time
steps while preserving performance. Experimental results show that, on image
segmentation and denoising, our Spiking-UNet achieves comparable performance to
its non-spiking counterpart, surpassing existing SNN methods. Compared with the
converted Spiking-UNet without fine-tuning, our Spiking-UNet reduces inference
time by approximately 90\%. This research broadens the application scope of
SNNs in image processing and is expected to inspire further exploration in the
field of neuromorphic engineering. The code for our Spiking-UNet implementation
is available at this https URL

本研究介绍了 Spiking-UNet 的概念，将 Spiking Neural Networks 与 U-Net 架构相结合，在图像处理任务中实现了高效的信息传输和训练策略，与非脉冲版本相比，在图像分割和去噪方面取得了可比较的性能，并且减少了推理时间。