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 https://github.com/SNNresearch/Spiking-UNet.

翻译：U-Net因其简单高效的架构而广泛应用于图像处理任务，尤其适合部署在神经形态芯片上。本文提出了用于图像处理的脉冲U-Net（Spiking-UNet）新概念，将脉冲神经网络（SNNs）的能力与U-Net架构相结合。为实现高效的Spiking-UNet，我们面临两个主要挑战：通过脉冲确保网络中的高保真信息传播，以及制定有效的训练策略。为解决信息丢失问题，我们引入了多阈值脉冲神经元，提高了Spiking-UNet内信息传输的效率。在训练策略方面，我们采用了基于预训练U-Net模型的转换与微调流水线。在转换过程中，我们观察到使用跳跃连接时不同部分的数据分布存在显著差异。因此，我们提出了一种连接级归一化方法以防止不准确的发放率。此外，我们采用基于流形的训练方法对转换后的模型进行微调，在减少时间步数的同时保持性能。实验结果表明，在图像分割和去噪任务中，我们的Spiking-UNet取得了与非脉冲U-Net相当的性能，超越了现有SNN方法。与未经微调的转换版Spiking-UNet相比，我们的Spiking-UNet将推理时间减少了约90%。本研究拓宽了SNNs在图像处理中的应用范围，有望推动神经形态工程领域的进一步探索。我们的Spiking-UNet实现代码已公布于https://github.com/SNNresearch/Spiking-UNet。