基于零件特征的变压器细粒度识别算法

Zhuangzhuang Feng, Wei Wu
{"title":"基于零件特征的变压器细粒度识别算法","authors":"Zhuangzhuang Feng, Wei Wu","doi":"10.1109/ICCECE58074.2023.10135351","DOIUrl":null,"url":null,"abstract":"Fine-grained image recognition is a challenging task. Due to the small differences between the categories of fine-grained images and the large differences within the categories, traditional networks based on CNN or Transformer have their own shortcomings in feature extraction. This paper gives full consideration to the characteristics of CNN and Transformer, and proposes a fine-grained recognition algorithm combining WS-DAN (Weakly Supervised Data Augmentation Network) and ViT (Vision Transformer). Firstly, the image patch is obtained by WS-DAN to eliminate the incomplete semantic information of image patch caused by traditional ViT. Then, the image patch is encoded based on Transformer framework and global token is introduced for topological relationship constraints among components, which overcomes the locality of features extracted from traditional CNN network. Finally, the training based on the combination of cross entropy and contrast loss function further improves the recognition ability of the network. The proposed algorithm has achieved satisfactory results on the CUB-200-2011, FGVC-Aircraft and Stanford Cars datasets.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fine-grained Recognition Algorithm For Transformer Based On Part Features\",\"authors\":\"Zhuangzhuang Feng, Wei Wu\",\"doi\":\"10.1109/ICCECE58074.2023.10135351\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Fine-grained image recognition is a challenging task. Due to the small differences between the categories of fine-grained images and the large differences within the categories, traditional networks based on CNN or Transformer have their own shortcomings in feature extraction. This paper gives full consideration to the characteristics of CNN and Transformer, and proposes a fine-grained recognition algorithm combining WS-DAN (Weakly Supervised Data Augmentation Network) and ViT (Vision Transformer). Firstly, the image patch is obtained by WS-DAN to eliminate the incomplete semantic information of image patch caused by traditional ViT. Then, the image patch is encoded based on Transformer framework and global token is introduced for topological relationship constraints among components, which overcomes the locality of features extracted from traditional CNN network. Finally, the training based on the combination of cross entropy and contrast loss function further improves the recognition ability of the network. The proposed algorithm has achieved satisfactory results on the CUB-200-2011, FGVC-Aircraft and Stanford Cars datasets.\",\"PeriodicalId\":120030,\"journal\":{\"name\":\"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCECE58074.2023.10135351\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCECE58074.2023.10135351","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

细粒度图像识别是一项具有挑战性的任务。由于细粒度图像的类别之间差异较小,类别内差异较大,因此基于CNN或Transformer的传统网络在特征提取方面存在各自的不足。本文充分考虑CNN和Transformer的特点,提出了一种结合WS-DAN(弱监督数据增强网络)和ViT(视觉变压器)的细粒度识别算法。首先,利用WS-DAN技术获取图像补丁,消除了传统ViT技术导致图像补丁语义信息不完整的问题;然后,基于Transformer框架对图像patch进行编码,并引入全局令牌对组件之间的拓扑关系进行约束,克服了传统CNN网络提取特征的局部性;最后,基于交叉熵和对比损失函数相结合的训练进一步提高了网络的识别能力。该算法在ub -200-2011、FGVC-Aircraft和Stanford Cars数据集上取得了满意的效果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Fine-grained Recognition Algorithm For Transformer Based On Part Features
Fine-grained image recognition is a challenging task. Due to the small differences between the categories of fine-grained images and the large differences within the categories, traditional networks based on CNN or Transformer have their own shortcomings in feature extraction. This paper gives full consideration to the characteristics of CNN and Transformer, and proposes a fine-grained recognition algorithm combining WS-DAN (Weakly Supervised Data Augmentation Network) and ViT (Vision Transformer). Firstly, the image patch is obtained by WS-DAN to eliminate the incomplete semantic information of image patch caused by traditional ViT. Then, the image patch is encoded based on Transformer framework and global token is introduced for topological relationship constraints among components, which overcomes the locality of features extracted from traditional CNN network. Finally, the training based on the combination of cross entropy and contrast loss function further improves the recognition ability of the network. The proposed algorithm has achieved satisfactory results on the CUB-200-2011, FGVC-Aircraft and Stanford Cars datasets.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信