Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval
Scalable image retrieval systems usually involve hierarchical quantization of local image descriptors, which produces a visual vocabulary for inverted indexing of images. Although hierarchical quantization has the merit of retrieval efficiency, the resulting visual vocabulary representation usually...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.6387 http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.180.6387 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.180.6387 2023-05-15T16:01:59+02:00 Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval Rongrong Ji Xing Xie Hongxun Yao Wei-ying Ma Heilongjiang P. R The Pennsylvania State University CiteSeerX Archives application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.6387 http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.6387 http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf text ftciteseerx 2016-01-07T16:27:34Z Scalable image retrieval systems usually involve hierarchical quantization of local image descriptors, which produces a visual vocabulary for inverted indexing of images. Although hierarchical quantization has the merit of retrieval efficiency, the resulting visual vocabulary representation usually faces two crucial problems: (1) hierarchical quantization errors and biases in the generation of “visual words"; (2) the model cannot adapt to database variance. In this paper, we describe an unsupervised optimization strategy in generating the hierarchy structure of visual vocabulary, which produces a more effective and adaptive retrieval model for large-scale search. We adopt a novel Density-based Metric Learning (DML) algorithm, which corrects word quantization bias without supervision in hierarchy optimization, based on which we present a hierarchical rejection chain for efficient online search based on the vocabulary hierarchy. We also discovered that by hierarchy optimization, efficient and effective transfer of a retrieval model across different databases is feasible. We deployed a large-scale image retrieval system using a vocabulary tree model to validate our advances. Experiments on UKBench and street-side urban scene databases demonstrated the effectiveness of our hierarchy optimization approach in comparison with state-of-the-art methods. 1. Text DML Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
description |
Scalable image retrieval systems usually involve hierarchical quantization of local image descriptors, which produces a visual vocabulary for inverted indexing of images. Although hierarchical quantization has the merit of retrieval efficiency, the resulting visual vocabulary representation usually faces two crucial problems: (1) hierarchical quantization errors and biases in the generation of “visual words"; (2) the model cannot adapt to database variance. In this paper, we describe an unsupervised optimization strategy in generating the hierarchy structure of visual vocabulary, which produces a more effective and adaptive retrieval model for large-scale search. We adopt a novel Density-based Metric Learning (DML) algorithm, which corrects word quantization bias without supervision in hierarchy optimization, based on which we present a hierarchical rejection chain for efficient online search based on the vocabulary hierarchy. We also discovered that by hierarchy optimization, efficient and effective transfer of a retrieval model across different databases is feasible. We deployed a large-scale image retrieval system using a vocabulary tree model to validate our advances. Experiments on UKBench and street-side urban scene databases demonstrated the effectiveness of our hierarchy optimization approach in comparison with state-of-the-art methods. 1. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Rongrong Ji Xing Xie Hongxun Yao Wei-ying Ma Heilongjiang P. R |
spellingShingle |
Rongrong Ji Xing Xie Hongxun Yao Wei-ying Ma Heilongjiang P. R Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval |
author_facet |
Rongrong Ji Xing Xie Hongxun Yao Wei-ying Ma Heilongjiang P. R |
author_sort |
Rongrong Ji |
title |
Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval |
title_short |
Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval |
title_full |
Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval |
title_fullStr |
Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval |
title_full_unstemmed |
Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval |
title_sort |
vocabulary hierarchy optimization for effective and transferable retrieval |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.6387 http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf |
genre |
DML |
genre_facet |
DML |
op_source |
http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.6387 http://vilab.hit.edu.cn/%7Errji/index_files/1184.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766397635512500224 |