The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Rangkaian saraf konvolusi (CNS) mempunyai keupayaan yang kuat untuk memahami dan menilai imej. Walau bagaimanapun, parameter dan pengiraan CNNS yang besar telah mengehadkan penggunaannya dalam peranti terhad sumber. Dalam surat ini, kami menggunakan idea perkongsian parameter dan sambungan padat untuk memampatkan parameter dalam arah saluran kernel lilitan, sekali gus mengurangkan bilangan parameter model. Atas dasar ini, kami mereka bentuk Rangkaian Konvolusial Bijak Saluran Kongsi dan Padat (SDChannelNets), terutamanya terdiri daripada lapisan Konvolusi SD-Saluran Boleh Asing Bijak Kedalaman. Kelebihan SDChannelNets ialah bilangan parameter model dikurangkan dengan banyak tanpa atau dengan sedikit kehilangan ketepatan. Kami juga memperkenalkan hiperparameter yang boleh mengimbangi bilangan parameter dan ketepatan model dengan berkesan. Kami menilai model yang dicadangkan oleh kami melalui dua tugas pengecaman imej yang popular (CIFAR-10 dan CIFAR-100). Keputusan menunjukkan bahawa SDChannelNets mempunyai ketepatan yang serupa dengan CNN lain, tetapi bilangan parameter telah dikurangkan dengan banyaknya.
JianNan ZHANG
Hangzhou Dianzi University
JiJun ZHOU
Hangzhou Dianzi University
JianFeng WU
Hangzhou Dianzi University
ShengYing YANG
Hangzhou Dianzi University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
JianNan ZHANG, JiJun ZHOU, JianFeng WU, ShengYing YANG, "SDChannelNets: Extremely Small and Efficient Convolutional Neural Networks" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 12, pp. 2646-2650, December 2019, doi: 10.1587/transinf.2019EDL8120.
Abstract: Convolutional neural networks (CNNS) have a strong ability to understand and judge images. However, the enormous parameters and computation of CNNS have limited its application in resource-limited devices. In this letter, we used the idea of parameter sharing and dense connection to compress the parameters in the convolution kernel channel direction, thus greatly reducing the number of model parameters. On this basis, we designed Shared and Dense Channel-wise Convolutional Networks (SDChannelNets), mainly composed of Depth-wise Separable SD-Channel-wise Convolution layer. The advantage of SDChannelNets is that the number of model parameters is greatly reduced without or with little loss of accuracy. We also introduced a hyperparameter that can effectively balance the number of parameters and the accuracy of a model. We evaluated the model proposed by us through two popular image recognition tasks (CIFAR-10 and CIFAR-100). The results showed that SDChannelNets had similar accuracy to other CNNs, but the number of parameters was greatly reduced.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8120/_p
Salinan
@ARTICLE{e102-d_12_2646,
author={JianNan ZHANG, JiJun ZHOU, JianFeng WU, ShengYing YANG, },
journal={IEICE TRANSACTIONS on Information},
title={SDChannelNets: Extremely Small and Efficient Convolutional Neural Networks},
year={2019},
volume={E102-D},
number={12},
pages={2646-2650},
abstract={Convolutional neural networks (CNNS) have a strong ability to understand and judge images. However, the enormous parameters and computation of CNNS have limited its application in resource-limited devices. In this letter, we used the idea of parameter sharing and dense connection to compress the parameters in the convolution kernel channel direction, thus greatly reducing the number of model parameters. On this basis, we designed Shared and Dense Channel-wise Convolutional Networks (SDChannelNets), mainly composed of Depth-wise Separable SD-Channel-wise Convolution layer. The advantage of SDChannelNets is that the number of model parameters is greatly reduced without or with little loss of accuracy. We also introduced a hyperparameter that can effectively balance the number of parameters and the accuracy of a model. We evaluated the model proposed by us through two popular image recognition tasks (CIFAR-10 and CIFAR-100). The results showed that SDChannelNets had similar accuracy to other CNNs, but the number of parameters was greatly reduced.},
keywords={},
doi={10.1587/transinf.2019EDL8120},
ISSN={1745-1361},
month={December},}
Salinan
TY - JOUR
TI - SDChannelNets: Extremely Small and Efficient Convolutional Neural Networks
T2 - IEICE TRANSACTIONS on Information
SP - 2646
EP - 2650
AU - JianNan ZHANG
AU - JiJun ZHOU
AU - JianFeng WU
AU - ShengYing YANG
PY - 2019
DO - 10.1587/transinf.2019EDL8120
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2019
AB - Convolutional neural networks (CNNS) have a strong ability to understand and judge images. However, the enormous parameters and computation of CNNS have limited its application in resource-limited devices. In this letter, we used the idea of parameter sharing and dense connection to compress the parameters in the convolution kernel channel direction, thus greatly reducing the number of model parameters. On this basis, we designed Shared and Dense Channel-wise Convolutional Networks (SDChannelNets), mainly composed of Depth-wise Separable SD-Channel-wise Convolution layer. The advantage of SDChannelNets is that the number of model parameters is greatly reduced without or with little loss of accuracy. We also introduced a hyperparameter that can effectively balance the number of parameters and the accuracy of a model. We evaluated the model proposed by us through two popular image recognition tasks (CIFAR-10 and CIFAR-100). The results showed that SDChannelNets had similar accuracy to other CNNs, but the number of parameters was greatly reduced.
ER -