基于更快残差多分支尖峰神经网络的高光谱图像分类技术

Yang Liu, Yahui Li, Rui Li, Liming Zhou, Lanxue Dang, Huiyu Mu, Qiang Ge
{"title":"基于更快残差多分支尖峰神经网络的高光谱图像分类技术","authors":"Yang Liu, Yahui Li, Rui Li, Liming Zhou, Lanxue Dang, Huiyu Mu, Qiang Ge","doi":"arxiv-2409.11619","DOIUrl":null,"url":null,"abstract":"Convolutional neural network (CNN) performs well in Hyperspectral Image (HSI)\nclassification tasks, but its high energy consumption and complex network\nstructure make it difficult to directly apply it to edge computing devices. At\npresent, spiking neural networks (SNN) have developed rapidly in HSI\nclassification tasks due to their low energy consumption and event driven\ncharacteristics. However, it usually requires a longer time step to achieve\noptimal accuracy. In response to the above problems, this paper builds a\nspiking neural network (SNN-SWMR) based on the leaky integrate-and-fire (LIF)\nneuron model for HSI classification tasks. The network uses the spiking width\nmixed residual (SWMR) module as the basic unit to perform feature extraction\noperations. The spiking width mixed residual module is composed of spiking\nmixed convolution (SMC), which can effectively extract spatial-spectral\nfeatures. Secondly, this paper designs a simple and efficient arcsine\napproximate derivative (AAD), which solves the non-differentiable problem of\nspike firing by fitting the Dirac function. Through AAD, we can directly train\nsupervised spike neural networks. Finally, this paper conducts comparative\nexperiments with multiple advanced HSI classification algorithms based on\nspiking neural networks on six public hyperspectral data sets. Experimental\nresults show that the AAD function has strong robustness and a good fitting\neffect. Meanwhile, compared with other algorithms, SNN-SWMR requires a time\nstep reduction of about 84%, training time, and testing time reduction of about\n63% and 70% at the same accuracy. This study solves the key problem of SNN\nbased HSI classification algorithms, which has important practical significance\nfor promoting the practical application of HSI classification algorithms in\nedge devices such as spaceborne and airborne devices.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Hyperspectral Image Classification Based on Faster Residual Multi-branch Spiking Neural Network\",\"authors\":\"Yang Liu, Yahui Li, Rui Li, Liming Zhou, Lanxue Dang, Huiyu Mu, Qiang Ge\",\"doi\":\"arxiv-2409.11619\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Convolutional neural network (CNN) performs well in Hyperspectral Image (HSI)\\nclassification tasks, but its high energy consumption and complex network\\nstructure make it difficult to directly apply it to edge computing devices. At\\npresent, spiking neural networks (SNN) have developed rapidly in HSI\\nclassification tasks due to their low energy consumption and event driven\\ncharacteristics. However, it usually requires a longer time step to achieve\\noptimal accuracy. In response to the above problems, this paper builds a\\nspiking neural network (SNN-SWMR) based on the leaky integrate-and-fire (LIF)\\nneuron model for HSI classification tasks. The network uses the spiking width\\nmixed residual (SWMR) module as the basic unit to perform feature extraction\\noperations. The spiking width mixed residual module is composed of spiking\\nmixed convolution (SMC), which can effectively extract spatial-spectral\\nfeatures. Secondly, this paper designs a simple and efficient arcsine\\napproximate derivative (AAD), which solves the non-differentiable problem of\\nspike firing by fitting the Dirac function. Through AAD, we can directly train\\nsupervised spike neural networks. Finally, this paper conducts comparative\\nexperiments with multiple advanced HSI classification algorithms based on\\nspiking neural networks on six public hyperspectral data sets. Experimental\\nresults show that the AAD function has strong robustness and a good fitting\\neffect. Meanwhile, compared with other algorithms, SNN-SWMR requires a time\\nstep reduction of about 84%, training time, and testing time reduction of about\\n63% and 70% at the same accuracy. This study solves the key problem of SNN\\nbased HSI classification algorithms, which has important practical significance\\nfor promoting the practical application of HSI classification algorithms in\\nedge devices such as spaceborne and airborne devices.\",\"PeriodicalId\":501289,\"journal\":{\"name\":\"arXiv - EE - Image and Video Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Image and Video Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11619\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11619","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

卷积神经网络(CNN)在高光谱图像(HSI)分类任务中表现出色,但其高能耗和复杂的网络结构使其难以直接应用于边缘计算设备。目前,尖峰神经网络(SNN)因其低能耗和事件驱动的特点,在高光谱图像分类任务中发展迅速。然而,它通常需要较长的时间步长才能达到最佳精度。针对上述问题,本文建立了一个基于泄漏积分-发射(LIF)神经元模型的尖峰神经网络(SNN-SWMR),用于人机界面分类任务。该网络使用尖峰宽度混合残差(SWMR)模块作为基本单元来执行特征提取操作。尖峰宽度混合残差模块由尖峰混合卷积(SMC)组成,能有效提取空间-光谱特征。其次,本文设计了一种简单高效的弧线近似导数(AAD),通过拟合狄拉克函数来解决尖峰发射的无差别问题。通过 AAD,我们可以直接训练有监督的尖峰神经网络。最后,本文在六个公开的高光谱数据集上进行了基于尖峰神经网络的多种高级 HSI 分类算法的对比实验。实验结果表明,AAD 函数具有较强的鲁棒性和良好的拟合效果。同时,与其他算法相比,在相同精度下,SNN-SWMR 所需的时间步骤减少了约 84%,训练时间和测试时间分别减少了约 63% 和 70%。该研究解决了基于 SNN 的人机交互分类算法的关键问题,对于推动人机交互分类算法在机载、空载等边缘设备中的实际应用具有重要的现实意义。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Hyperspectral Image Classification Based on Faster Residual Multi-branch Spiking Neural Network
Convolutional neural network (CNN) performs well in Hyperspectral Image (HSI) classification tasks, but its high energy consumption and complex network structure make it difficult to directly apply it to edge computing devices. At present, spiking neural networks (SNN) have developed rapidly in HSI classification tasks due to their low energy consumption and event driven characteristics. However, it usually requires a longer time step to achieve optimal accuracy. In response to the above problems, this paper builds a spiking neural network (SNN-SWMR) based on the leaky integrate-and-fire (LIF) neuron model for HSI classification tasks. The network uses the spiking width mixed residual (SWMR) module as the basic unit to perform feature extraction operations. The spiking width mixed residual module is composed of spiking mixed convolution (SMC), which can effectively extract spatial-spectral features. Secondly, this paper designs a simple and efficient arcsine approximate derivative (AAD), which solves the non-differentiable problem of spike firing by fitting the Dirac function. Through AAD, we can directly train supervised spike neural networks. Finally, this paper conducts comparative experiments with multiple advanced HSI classification algorithms based on spiking neural networks on six public hyperspectral data sets. Experimental results show that the AAD function has strong robustness and a good fitting effect. Meanwhile, compared with other algorithms, SNN-SWMR requires a time step reduction of about 84%, training time, and testing time reduction of about 63% and 70% at the same accuracy. This study solves the key problem of SNN based HSI classification algorithms, which has important practical significance for promoting the practical application of HSI classification algorithms in edge devices such as spaceborne and airborne devices.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
multiPI-TransBTS: A Multi-Path Learning Framework for Brain Tumor Image Segmentation Based on Multi-Physical Information Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CT Denoising diffusion models for high-resolution microscopy image restoration Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation using Rein to Fine-tune Vision Foundation Models
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1