arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.02258cs.CV
收藏

探索脉冲神经网络在图像去雨中的潜力

Exploring the Potentials of Spiking Neural Networks for Image Deraining

Shuang Chen, Tomas Krajnik, Farshad Arvin, Amir Atapour-Abarghouei

AI总结:

本文提出视觉泄漏积分神经元和多尺度模块,利用脉冲神经网络在低级视觉任务中实现高效去雨,以13%的能量消耗超越现有方法。

摘要:

生物合理且节能的框架,如脉冲神经网络(SNNs),在低级视觉任务中尚未得到充分探索。以图像去雨为例,本研究针对脉冲神经元固有的高频特性进行表示,特别是在图像去雨中,创新性地提出了视觉泄漏积分(VLIF)神经元,克服了传统脉冲神经元缺乏空间上下文理解的障碍。为解决传统脉冲神经元固有频率域饱和的限制,我们利用所提出的VLIF引入了脉冲分解与增强模块和轻量级脉冲多尺度单元,用于层次化多尺度表示学习。在五个基准去雨数据集上的广泛实验表明,我们的方法在性能上显著优于最先进的SNN去雨方法,仅以13%的能量消耗实现了优越的性能。这些发现为在高性能、节能的低级视觉任务中部署SNNs奠定了坚实基础。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑