零射击识别的双曲视觉嵌入学习

Shaoteng Liu, Jingjing Chen, Liangming Pan, C. Ngo, Tat-seng Chua, Yu-Gang Jiang
{"title":"零射击识别的双曲视觉嵌入学习","authors":"Shaoteng Liu, Jingjing Chen, Liangming Pan, C. Ngo, Tat-seng Chua, Yu-Gang Jiang","doi":"10.1109/cvpr42600.2020.00929","DOIUrl":null,"url":null,"abstract":"This paper proposes a Hyperbolic Visual Embedding Learning Network for zero-shot recognition. The network learns image embeddings in hyperbolic space, which is capable of preserving the hierarchical structure of semantic classes in low dimensions. Comparing with existing zero-shot learning approaches, the network is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings. Our network outperforms exiting baselines under hierarchical evaluation with an extremely challenging setting, \\textit{i.e.,} learning only from 1,000 categories to recognize 20,841 unseen categories. While under flat evaluation, it has competitive performance as state-of-the-art methods but with five times lower embedding dimensions. Our code is publicly available \\footnote{\\url{https://github.com/ShaoTengLiu/Hyperbolic_ZSL}}.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"12 1","pages":"9270-9278"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"93","resultStr":"{\"title\":\"Hyperbolic Visual Embedding Learning for Zero-Shot Recognition\",\"authors\":\"Shaoteng Liu, Jingjing Chen, Liangming Pan, C. Ngo, Tat-seng Chua, Yu-Gang Jiang\",\"doi\":\"10.1109/cvpr42600.2020.00929\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a Hyperbolic Visual Embedding Learning Network for zero-shot recognition. The network learns image embeddings in hyperbolic space, which is capable of preserving the hierarchical structure of semantic classes in low dimensions. Comparing with existing zero-shot learning approaches, the network is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings. Our network outperforms exiting baselines under hierarchical evaluation with an extremely challenging setting, \\\\textit{i.e.,} learning only from 1,000 categories to recognize 20,841 unseen categories. While under flat evaluation, it has competitive performance as state-of-the-art methods but with five times lower embedding dimensions. Our code is publicly available \\\\footnote{\\\\url{https://github.com/ShaoTengLiu/Hyperbolic_ZSL}}.\",\"PeriodicalId\":6715,\"journal\":{\"name\":\"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)\",\"volume\":\"12 1\",\"pages\":\"9270-9278\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"93\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/cvpr42600.2020.00929\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/cvpr42600.2020.00929","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 93

摘要

提出了一种用于零射击识别的双曲视觉嵌入学习网络。该网络在双曲空间中学习图像嵌入,能够在低维空间中保持语义类的层次结构。与现有的零次学习方法相比,该网络的鲁棒性更强,因为双曲空间的嵌入特征更好地代表了类的层次结构,从而避免了不相关的兄弟姐妹带来的误导。我们的网络在一个极具挑战性的设置下,在分层评估下优于现有的基线,\textit{即}仅从1,000个类别中学习以识别20,841个未见过的类别。在扁平化评价下,它具有与最先进的方法相媲美的性能,但嵌入维数降低了5倍。我们的代码是公开的\footnote{\url{https://github.com/ShaoTengLiu/Hyperbolic_ZSL}}。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Hyperbolic Visual Embedding Learning for Zero-Shot Recognition
This paper proposes a Hyperbolic Visual Embedding Learning Network for zero-shot recognition. The network learns image embeddings in hyperbolic space, which is capable of preserving the hierarchical structure of semantic classes in low dimensions. Comparing with existing zero-shot learning approaches, the network is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings. Our network outperforms exiting baselines under hierarchical evaluation with an extremely challenging setting, \textit{i.e.,} learning only from 1,000 categories to recognize 20,841 unseen categories. While under flat evaluation, it has competitive performance as state-of-the-art methods but with five times lower embedding dimensions. Our code is publicly available \footnote{\url{https://github.com/ShaoTengLiu/Hyperbolic_ZSL}}.
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