Improved SVM-AdaBoost Stacking Algorithm with ResNet18

Minxian Wei, Yuezu Lv, Jialing Zhou

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Image classification with small amount of data has become a key issue in computer vision. In this paper, a novel stacking architecture based on support vector machine (SVM) and adaptive boosting (AdaBoost) is proposed. The 18-layer ResNet model is used to extract features, acting as the input of the stacking algorithm. Then, the SVM classifiers in the first layer produce the basic predictions, based on which, the AdaBoost classifier in the second layer decides the final class of image. Experimental results on CIFAR-10 dataset demonstrate that the SVM-AdaBoost stacking algorithm outperforms the existing competitive benchmark algorithms with single SVM or AdaBoost.

源语言英语
主期刊名Proceedings of 2021 IEEE International Conference on Unmanned Systems, ICUS 2021
出版商Institute of Electrical and Electronics Engineers Inc.
16-20
页数5
ISBN(电子版)9780738146577
DOI
出版状态已出版 - 2021
已对外发布
活动2021 IEEE International Conference on Unmanned Systems, ICUS 2021 - Beijing, 中国
期限: 15 10月 202117 10月 2021

出版系列

姓名Proceedings of 2021 IEEE International Conference on Unmanned Systems, ICUS 2021

会议

会议2021 IEEE International Conference on Unmanned Systems, ICUS 2021
国家/地区中国
Beijing
时期15/10/2117/10/21

指纹

探究 'Improved SVM-AdaBoost Stacking Algorithm with ResNet18' 的科研主题。它们共同构成独一无二的指纹。

引用此