CN2Conv：面向物聯(lián)網(wǎng)設(shè)備的強(qiáng)魯棒CNN設(shè)計(jì)方法

打開(kāi)文本圖片集

關(guān)鍵詞：卷積神經(jīng)網(wǎng)絡(luò)；云輔助訓(xùn)練；少參數(shù)模型；魯棒性

中圖分類號(hào)：TP183 文獻(xiàn)標(biāo)志碼：A 文章編號(hào)：1001-3695（2025）07-031-2154-07

doi： 10.19734/j . issn.1001-3695.2024.12.0500

Abstract：Theuseofcloud-assisted training forCNN with fewparameterscanenable theirdeploymentonresource-constrained IoTdevices.However，existing models with fewparameters suferfrom insuficientabilitytoextractcomplexdatafeatures and poor robustnessThis article proposed a CNN design method that was adaptable to complexdata and hadstrong robustness， calledthecombinednon-linearityconvolution kernelgeneration（CN2Conv）.Firstly，itrandomlyselectedsomeconvolution kernels fromtheconvolutionallayersoftheCNNmodelasseedconvolution kernels，andusedmultiplegeneration functions to performonlinear transformationsontheseedconvolution kernels toobtain diversegenerationconvolution kernels.Secondly， thediferentgenerationfunctionsuseddiferenthyperparameterstocontroltheregularizationeffectofthemodelandiproved itsrobustness.Finall，itusedthefeatureapsgeneratedbytheconvoutionalkernls toperformchannelsuflingadconvlutional dimensionalityreductionoperations，whileusinggroupnormalization techniques toimprovethedistributionconsistency offeaturesandenhancetheabilitytocapturecomplex data features.InordertoverifytheefectivenessofCN2Conv，this paper carried outseveral experimentson CIFAR-10，CIFAR-1O0，CIFAR-10-Cand Icons-50datasets.Onthe CIFAR-10-C dataset， the accuracy of ResNet34 using CN2Conv is 8. 22% higher than the standard ResNet34，and 11. 86% higher than MonoCNN. Theresultsshowthatthe accuracyof the CNN modelbasedon CN2Convis beterthanthecomparison method on multiple datasets，and the robustness is significantly improved.

Key words：convolutional neural network （CNN）；cloud-asisted training；less parameter model; robustness

0 引言

根據(jù)IDC最新發(fā)布的報(bào)告《WorldwideGlobalDataSphereIoTDeviceandDataForecast，2023—2027》顯示[1，隨著物聯(lián)網(wǎng)技術(shù)的持續(xù)進(jìn)步和廣泛應(yīng)用，全球物聯(lián)網(wǎng)設(shè)備的數(shù)量預(yù)計(jì)將從2023年的167億臺(tái)激增至2027年的290億臺(tái)，其中2024年將達(dá)到190億臺(tái)。（剩余17424字）