广义相关性学习格拉斯曼量化

M Mohammadi, M Babai, M H F Wilkinson
{"title":"广义相关性学习格拉斯曼量化","authors":"M Mohammadi, M Babai, M H F Wilkinson","doi":"10.1109/TPAMI.2024.3466315","DOIUrl":null,"url":null,"abstract":"<p><p>Due to advancements in digital cameras, it is easy to gather multiple images (or videos) from an object under different conditions. Therefore, image-set classification has attracted more attention, and different solutions were proposed to model them. A popular way to model image sets is subspaces, which form a manifold called the Grassmann manifold. In this contribution, we extend the application of Generalized Relevance Learning Vector Quantization to deal with Grassmann manifold. The proposed model returns a set of prototype subspaces and a relevance vector. While prototypes model typical behaviours within classes, the relevance factors specify the most discriminative principal vectors (or images) for the classification task. They both provide insights into the model's decisions by highlighting influential images and pixels for predictions. Moreover, due to learning prototypes, the model complexity of the new method during inference is independent of dataset size, unlike previous works. We applied it to several recognition tasks including handwritten digit recognition, face recognition, activity recognition, and object recognition. Experiments demonstrate that it outperforms previous works with lower complexity and can successfully model the variation, such as handwritten style or lighting conditions. Moreover, the presence of relevances makes the model robust to the selection of subspaces' dimensionality.</p>","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":"PP ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generalized Relevance Learning Grassmann Quantization.\",\"authors\":\"M Mohammadi, M Babai, M H F Wilkinson\",\"doi\":\"10.1109/TPAMI.2024.3466315\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Due to advancements in digital cameras, it is easy to gather multiple images (or videos) from an object under different conditions. Therefore, image-set classification has attracted more attention, and different solutions were proposed to model them. A popular way to model image sets is subspaces, which form a manifold called the Grassmann manifold. In this contribution, we extend the application of Generalized Relevance Learning Vector Quantization to deal with Grassmann manifold. The proposed model returns a set of prototype subspaces and a relevance vector. While prototypes model typical behaviours within classes, the relevance factors specify the most discriminative principal vectors (or images) for the classification task. They both provide insights into the model's decisions by highlighting influential images and pixels for predictions. Moreover, due to learning prototypes, the model complexity of the new method during inference is independent of dataset size, unlike previous works. We applied it to several recognition tasks including handwritten digit recognition, face recognition, activity recognition, and object recognition. Experiments demonstrate that it outperforms previous works with lower complexity and can successfully model the variation, such as handwritten style or lighting conditions. Moreover, the presence of relevances makes the model robust to the selection of subspaces' dimensionality.</p>\",\"PeriodicalId\":94034,\"journal\":{\"name\":\"IEEE transactions on pattern analysis and machine intelligence\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on pattern analysis and machine intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TPAMI.2024.3466315\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TPAMI.2024.3466315","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

由于数码相机的进步,从一个物体上收集不同条件下的多幅图像(或视频)变得非常容易。因此,图像集分类受到越来越多的关注,并提出了不同的建模方案。子空间是图像集建模的一种常用方法,它构成了一种叫做格拉斯曼流形的流形。在本文中,我们扩展了广义相关性学习矢量量化的应用,以处理格拉斯曼流形。所提出的模型会返回一组原型子空间和一个相关性向量。原型为类别内的典型行为建模,而相关性因子则指定了分类任务中最具区分度的主向量(或图像)。它们都通过突出对预测有影响的图像和像素,为模型的决策提供洞察力。此外,由于学习原型的存在,新方法在推理过程中的模型复杂度与数据集大小无关,这与之前的研究不同。我们将其应用于多项识别任务,包括手写数字识别、人脸识别、活动识别和物体识别。实验证明,该方法以较低的复杂度超越了之前的研究成果,并能成功模拟手写风格或光照条件等变化。此外,相关性的存在使模型对子空间维度的选择具有鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Generalized Relevance Learning Grassmann Quantization.

Due to advancements in digital cameras, it is easy to gather multiple images (or videos) from an object under different conditions. Therefore, image-set classification has attracted more attention, and different solutions were proposed to model them. A popular way to model image sets is subspaces, which form a manifold called the Grassmann manifold. In this contribution, we extend the application of Generalized Relevance Learning Vector Quantization to deal with Grassmann manifold. The proposed model returns a set of prototype subspaces and a relevance vector. While prototypes model typical behaviours within classes, the relevance factors specify the most discriminative principal vectors (or images) for the classification task. They both provide insights into the model's decisions by highlighting influential images and pixels for predictions. Moreover, due to learning prototypes, the model complexity of the new method during inference is independent of dataset size, unlike previous works. We applied it to several recognition tasks including handwritten digit recognition, face recognition, activity recognition, and object recognition. Experiments demonstrate that it outperforms previous works with lower complexity and can successfully model the variation, such as handwritten style or lighting conditions. Moreover, the presence of relevances makes the model robust to the selection of subspaces' dimensionality.

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