基于迁移学习的鸟类细粒度特征提取

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI:10.1109/ICSAI53574.2021.9664058

Peng Wu, Gang Wu

{"title":"基于迁移学习的鸟类细粒度特征提取","authors":"Peng Wu, Gang Wu","doi":"10.1109/ICSAI53574.2021.9664058","DOIUrl":null,"url":null,"abstract":"The KLt-SNE algorithm is based on Kullback-Leibler divergence and t-SNE. Give an unknown distribution <tex>$p(x)$</tex>, at first, and then establish a <tex>$q\\, (x\\vert \\theta)$</tex>, with the same dimension as the unknown distribution, estimate the parameter <tex>$\\theta$</tex> that needs to be configured by taking <tex>$N$</tex> samples from <tex>$p(x)$</tex>. The results show that this algorithm can effectively achieve dimensionality reduction of data.","PeriodicalId":131284,"journal":{"name":"2021 7th International Conference on Systems and Informatics (ICSAI)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Birds Fine-grained Feature Extraction Based on Transfer Learning\",\"authors\":\"Peng Wu, Gang Wu\",\"doi\":\"10.1109/ICSAI53574.2021.9664058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The KLt-SNE algorithm is based on Kullback-Leibler divergence and t-SNE. Give an unknown distribution <tex>$p(x)$</tex>, at first, and then establish a <tex>$q\\\\, (x\\\\vert \\\\theta)$</tex>, with the same dimension as the unknown distribution, estimate the parameter <tex>$\\\\theta$</tex> that needs to be configured by taking <tex>$N$</tex> samples from <tex>$p(x)$</tex>. The results show that this algorithm can effectively achieve dimensionality reduction of data.\",\"PeriodicalId\":131284,\"journal\":{\"name\":\"2021 7th International Conference on Systems and Informatics (ICSAI)\",\"volume\":\"80 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 7th International Conference on Systems and Informatics (ICSAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSAI53574.2021.9664058\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 7th International Conference on Systems and Informatics (ICSAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSAI53574.2021.9664058","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

KLt-SNE算法基于Kullback-Leibler散度和t-SNE。首先给出一个未知分布$p(x)$，然后建立一个与未知分布具有相同维数的$q\， (x\vert \theta)$，通过从$p(x)$中取$N$样本来估计需要配置的参数$\theta$。结果表明，该算法能有效地实现数据的降维。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Birds Fine-grained Feature Extraction Based on Transfer Learning

The KLt-SNE algorithm is based on Kullback-Leibler divergence and t-SNE. Give an unknown distribution $p(x)$, at first, and then establish a $q\, (x\vert \theta)$, with the same dimension as the unknown distribution, estimate the parameter $\theta$ that needs to be configured by taking $N$ samples from $p(x)$. The results show that this algorithm can effectively achieve dimensionality reduction of data.

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

2021 7th International Conference on Systems and Informatics (ICSAI)

自引率

0.00%

发文量