Undo the codebook bias by linear transformation for visual applications

Chunjie Zhang, Yifan Zhang, Shuhui Wang, Junbiao Pang, Chao Liang, Qingming Huang, Q. Tian
{"title":"Undo the codebook bias by linear transformation for visual applications","authors":"Chunjie Zhang, Yifan Zhang, Shuhui Wang, Junbiao Pang, Chao Liang, Qingming Huang, Q. Tian","doi":"10.1145/2502081.2502141","DOIUrl":null,"url":null,"abstract":"The bag of visual words model (BoW) and its variants have demonstrate their effectiveness for visual applications and have been widely used by researchers. The BoW model first extracts local features and generates the corresponding codebook, the elements of a codebook are viewed as visual words. The local features within each image are then encoded to get the final histogram representation. However, the codebook is dataset dependent and has to be generated for each image dataset. This costs a lot of computational time and weakens the generalization power of the BoW model. To solve these problems, in this paper, we propose to undo the dataset bias by codebook linear transformation. To represent every points within the local feature space using Euclidean distance, the number of bases should be no less than the space dimensions. Hence, each codebook can be viewed as a linear transformation of these bases. In this way, we can transform the pre-learned codebooks for a new dataset. However, not all of the visual words are equally important for the new dataset, it would be more effective if we can make some selection using sparsity constraints and choose the most discriminative visual words for transformation. We propose an alternative optimization algorithm to jointly search for the optimal linear transformation matrixes and the encoding parameters. Image classification experimental results on several image datasets show the effectiveness of the proposed method.","PeriodicalId":20448,"journal":{"name":"Proceedings of the 21st ACM international conference on Multimedia","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 21st ACM international conference on Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2502081.2502141","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

The bag of visual words model (BoW) and its variants have demonstrate their effectiveness for visual applications and have been widely used by researchers. The BoW model first extracts local features and generates the corresponding codebook, the elements of a codebook are viewed as visual words. The local features within each image are then encoded to get the final histogram representation. However, the codebook is dataset dependent and has to be generated for each image dataset. This costs a lot of computational time and weakens the generalization power of the BoW model. To solve these problems, in this paper, we propose to undo the dataset bias by codebook linear transformation. To represent every points within the local feature space using Euclidean distance, the number of bases should be no less than the space dimensions. Hence, each codebook can be viewed as a linear transformation of these bases. In this way, we can transform the pre-learned codebooks for a new dataset. However, not all of the visual words are equally important for the new dataset, it would be more effective if we can make some selection using sparsity constraints and choose the most discriminative visual words for transformation. We propose an alternative optimization algorithm to jointly search for the optimal linear transformation matrixes and the encoding parameters. Image classification experimental results on several image datasets show the effectiveness of the proposed method.
通过可视化应用程序的线性变换来撤消码本偏差
视觉词包模型(BoW)及其变体已经证明了其在视觉应用中的有效性,并被研究者广泛使用。BoW模型首先提取局部特征并生成相应的码本,码本中的元素被视为视觉词。然后对每个图像中的局部特征进行编码以获得最终的直方图表示。然而,码本是数据集相关的,必须为每个图像数据集生成。这不仅耗费了大量的计算时间,而且削弱了BoW模型的泛化能力。为了解决这些问题,本文提出了通过码本线性变换来消除数据集偏差的方法。为了用欧氏距离表示局部特征空间中的每一个点,基的数目应不小于空间的维数。因此,每个码本都可以看作是这些基的线性变换。通过这种方式,我们可以将预学习的代码本转换为新的数据集。然而,并不是所有的视觉词对新数据集都同样重要,如果我们可以使用稀疏性约束进行一些选择,并选择最具判别性的视觉词进行转换,将会更有效。我们提出了一种替代优化算法来联合搜索最优线性变换矩阵和编码参数。在多个图像数据集上的图像分类实验结果表明了该方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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