Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval

Olivier Morère, Jie Lin, A. Veillard, V. Chandrasekhar
{"title":"Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval","authors":"Olivier Morère, Jie Lin, A. Veillard, V. Chandrasekhar","doi":"10.1145/3078971.3078987","DOIUrl":null,"url":null,"abstract":"The goal of this work is the computation of very compact binary hashes for image instance retrieval. Our approach has two novel contributions. The first one is Nested Invariance Pooling (NIP), a method inspired from i-theory, a mathematical theory for computing group invariant transformations with feed-forward neural networks. NIP is able to produce compact and well-performing descriptors with visual representations extracted from convolutional neural networks. We specifically incorporate scale, translation and rotation invariances but the scheme can be extended to any arbitrary sets of transformations. We also show that using moments of increasing order throughout nesting is important. The NIP descriptors are then hashed to the target code size (32-256 bits) with a Restricted Boltzmann Machine with a novel batch-level regularization scheme specifically designed for the purpose of hashing (RBMH). A thorough empirical evaluation with state-of-the-art shows that the results obtained both with the NIP descriptors and the NIP+RBMH hashes are consistently outstanding across a wide range of datasets.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3078971.3078987","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 16

Abstract

The goal of this work is the computation of very compact binary hashes for image instance retrieval. Our approach has two novel contributions. The first one is Nested Invariance Pooling (NIP), a method inspired from i-theory, a mathematical theory for computing group invariant transformations with feed-forward neural networks. NIP is able to produce compact and well-performing descriptors with visual representations extracted from convolutional neural networks. We specifically incorporate scale, translation and rotation invariances but the scheme can be extended to any arbitrary sets of transformations. We also show that using moments of increasing order throughout nesting is important. The NIP descriptors are then hashed to the target code size (32-256 bits) with a Restricted Boltzmann Machine with a novel batch-level regularization scheme specifically designed for the purpose of hashing (RBMH). A thorough empirical evaluation with state-of-the-art shows that the results obtained both with the NIP descriptors and the NIP+RBMH hashes are consistently outstanding across a wide range of datasets.
用于图像实例检索的嵌套不变性池和RBM哈希
这项工作的目标是计算非常紧凑的二进制哈希图像实例检索。我们的方法有两个新的贡献。第一种是嵌套不变量池(NIP),这是一种受i-theory启发的方法,i-theory是一种用前馈神经网络计算群不变变换的数学理论。NIP能够使用从卷积神经网络中提取的视觉表示生成紧凑且性能良好的描述符。我们特别结合了尺度、平移和旋转不变性,但该方案可以扩展到任意变换集。我们还展示了在整个嵌套过程中使用增加顺序的时刻是很重要的。NIP描述符然后用受限玻尔兹曼机(Restricted Boltzmann Machine)散列到目标代码大小(32-256位),该机具有专门为散列目的(RBMH)设计的新型批处理级正则化方案。全面的经验评估与最先进的技术表明,NIP描述符和NIP+RBMH哈希所获得的结果在广泛的数据集上始终是杰出的。
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:604180095
Book学术官方微信