提出新型脉冲神经元，让低功耗神经网络更高效地去除图像雨痕。
Exploring the Potentials of Spiking Neural Networks for Image Deraining
- 设计视觉型脉冲神经元（VLIF），解决传统脉冲神经元缺乏空间上下文理解的问题。
- 在5个基准数据集上性能超越当前最优脉冲网络方法，能耗仅为13%。
- 适合关注低功耗视觉任务的科研与工程人员参考。
生物可解释且能效高的脉冲神经网络（SNNs）在低层视觉任务中尚未得到充分探索。以图像去雨为例，本文针对脉冲神经元固有的高通特性进行建模，创新性地提出视觉型脉冲神经元（VLIF），克服了传统脉冲神经元缺乏空间上下文理解的瓶颈。为解决传统脉冲神经元频域饱和问题，我们基于VLIF构建了脉冲分解与增强模块及轻量级多尺度单元，实现分层多尺度表征学习。在五个基准去雨数据集上的大量实验表明，该方法显著优于现有SNN-based去雨方法，在仅消耗其13%能耗的前提下实现了卓越性能。这些成果为将SNN部署于高性能、低功耗的低层视觉任务奠定了坚实基础。
原文摘要 · Abstract (English)
Biologically plausible and energy-efficient frameworks such as Spiking Neural Networks (SNNs) have not been sufficiently explored in low-level vision tasks. Taking image deraining as an example, this study addresses the representation of the inherent high-pass characteristics of spiking neurons, specifically in image deraining and innovatively proposes the Visual LIF (VLIF) neuron, overcoming the obstacle of lacking spatial contextual understanding present in traditional spiking neurons. To tackle the limitation of frequency-domain saturation inherent in conventional spiking neurons, we leverage the proposed VLIF to introduce the Spiking Decomposition and Enhancement Module and the lightweight Spiking Multi-scale Unit for hierarchical multi-scale representation learning. Extensive experiments across five benchmark deraining datasets demonstrate that our approach significantly outperforms state-of-the-art SNN-based deraining methods, achieving this superior performance with only 13\% of their energy consumption. These findings establish a solid foundation for deploying SNNs in high-performance, energy-efficient low-level vision tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。