tutorial

Improving the Quality of K-NN Graphs for Image Databases through Vector Sparsification

Authors:

Michael E. Houle,

Jichao SunAuthors Info & Claims

ICMR '14: Proceedings of International Conference on Multimedia Retrieval

Pages 89 - 96

https://doi.org/10.1145/2578726.2578730

Published: 01 April 2014 Publication History

Abstract

Neighborhood graphs are an essential component of many established methods for content-based image retrieval and automated image annotation. The performance of such methods relies heavily on the semantic quality of the graphs, which can be measured as the proportion of neighbors sharing the same class label as their query images. In this paper, we propose a new framework for the efficient construction of K-nearest neighbor (K-NN) graphs based on nearest-neighbor descent (NN-Descent), in which selective sparsification of object feature vectors is interleaved with neighborhood refinement operations in an effort to improve the semantic quality of the result. A local variant of the Laplacian Score is used to identify noisy features with respect to individual images, whose values are then set to 0 (the global mean value after standardization). We show through extensive experiments that our graph construction method is able to increase the proportion of semantically-related images over unrelated images within the neighbor sets.

References

[1]

M. Belkin and P. Niyogi. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 15(6):1373--1396, 2003.

Digital Library

[2]

M. Brito, E. Chávez, A. Quiroz, and J. Yukich. Connectivity of the mutual k-nearest-neighbor graph in clustering and outlier detection. Statistics & Probability Letters, 35(1):33--42, 1997.

[3]

W. Dong, M. Charikar, and K. Li. Efficient k-nearest neighbor graph construction for generic similarity measures. In Proceedings of the 20th International Conference on World Wide Web, pages 577--586, 2011.

Digital Library

[4]

J.-M. Geusebroek, G. J. Burghouts, and A. W. M. Smeulders. The Amsterdam Library of Object Images. Int. J. Comput. Vision, 61(1):103--112, January 2005.

Digital Library

[5]

R. He, Y. Zhu, and W. Zhan. Fast manifold-ranking for content-based image retrieval. In ISECS International Colloquium on Computing, Communication, Control, and Management, volume 2, pages 299--302, 2009.

[6]

X. He, D. Cai, and P. Niyogi. Laplacian score for feature selection. In Advances in Neural Information Processing Systems 18, pages 507--514. MIT Press, 2006.

[7]

M. E. Houle, V. Oria, S. Satoh, and J. Sun. Knowledge propagation in large image databases using neighborhood information. In Proceedings of the ACM Multimedia, pages 1033--1036, 2011.

Digital Library

[8]

R. Kohavi and G. H. John. Wrappers for feature subset selection. Artif. Intell., 97(1-2):273--324, 1997.

Digital Library

[9]

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proc. IEEE, 86(11):2278--2324, 1998.

[10]

D. Qin, S. Gammeter, L. Bossard, T. Quack, and L. J. V. Gool. Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. In Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, pages 777--784, 2011.

Digital Library

[11]

M. Robnik-Sikonja and I. Kononenko. Theoretical and empirical analysis of ReliefF and RReliefF. Machine Learning, 53(1-2):23--69, 2003.

Digital Library

[12]

F. S. Samaria and A. C. Harter. Parameterisation of a stochastic model for human face identification. In Proceedings of the Second IEEE Workshop on Applications of Computer Vision, pages 138--142, 1994.

[13]

J. Tang, R. Hong, S. Yan, T.-S. Chua, G.-J. Qi, and R. Jain. Image annotation by kNN-sparse graph-based label propagation over noisily tagged web images. ACM Trans. Intell. Syst. Technol., 2(2):14, 2011.

Digital Library

[14]

H. Tong, J. He, M. Li, W.-Y. Ma, H.-J. Zhang, and C. Zhang. Manifold-ranking-based keyword propagation for image retrieval. EURASIP J. Adv. Sig. Proc., 2006, 2006.

Digital Library

[15]

Z. Zhao and H. Liu. Spectral feature selection for supervised and unsupervised learning. In Proceedings of the 24th International Conference on Machine Learning, pages 1151--1157, 2007.

Digital Library

[16]

X. Zhu, Z. Ghahramani, and J. D. Lafferty. Semi-supervised learning using gaussian fields and harmonic functions. In Proceedings of the 20th International Conference on Machine Learning, pages 912--919, 2003.

Digital Library

Cited By

Liu CLiao XZheng LHuang YLiu HZhang YHe HHuang HZhou JJin H(2024)L-FNNG: Accelerating Large-Scale KNN Graph Construction on CPU-FPGA Heterogeneous PlatformACM Transactions on Reconfigurable Technology and Systems10.1145/365260917:3(1-29)Online publication date: 14-Mar-2024
https://dl.acm.org/doi/10.1145/3652609
Liu CLiu HZheng LHuang YYe XLiao XJin HIenne PZhang Z(2023)FNNG: A High-Performance FPGA-based Accelerator for K-Nearest Neighbor Graph ConstructionProceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays10.1145/3543622.3573189(67-77)Online publication date: 12-Feb-2023
https://dl.acm.org/doi/10.1145/3543622.3573189
Wu XLiu SBai Y(2023)The manifold regularized SVDD for noisy label detectionInformation Sciences: an International Journal10.1016/j.ins.2022.10.109619:C(235-248)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1016/j.ins.2022.10.109
Show More Cited By

Index Terms

Improving the Quality of K-NN Graphs for Image Databases through Vector Sparsification
1. Information systems
  1. Information systems applications
    1. Multimedia information systems
      1. Multimedia databases

Recommendations

Local Selection of Features for Image Search and Annotation
MM '14: Proceedings of the 22nd ACM international conference on Multimedia

In image applications, direct representations of images typically involve hundreds or thousands of features and not all the features are relevant for any given object. Errors introduced into similarity measurements by irrelevant or noisy features are ...
L2Knng: Fast Exact K-Nearest Neighbor Graph Construction with L2-Norm Pruning
CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

The k-nearest neighbor graph is often used as a building block in information retrieval, clustering, online advertising, and recommender systems algorithms. The complexity of constructing the exact k-nearest neighbor graph is quadratic on the number of ...
AnnexML: Approximate Nearest Neighbor Search for Extreme Multi-label Classification
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Extreme multi-label classification methods have been widely used in Web-scale classification tasks such as Web page tagging and product recommendation. In this paper, we present a novel graph embedding method called "AnnexML". At the training step, ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICMR '14: Proceedings of International Conference on Multimedia Retrieval

April 2014

564 pages

ISBN:9781450327824

DOI:10.1145/2578726

Conference Chairs:
Mohan Kankanhalli
National University of Singapore
,
Stefan Rueger
The Open University, UK
,
R. Manmatha
A9.com, USA
,
General Chairs:
Joemon Jose
University of Glasgow, UK
,
Keith van Rijsbergen
University of Glasgow, UK

Copyright © 2014 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 April 2014

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Tutorial
Research
Refereed limited

Conference

ICMR '14

ICMR '14: International Conference on Multimedia Retrieval

April 1 - 4, 2014

Glasgow, United Kingdom

Acceptance Rates

ICMR '14 Paper Acceptance Rate 21 of 111 submissions, 19%;

Overall Acceptance Rate 254 of 830 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
159
Total Downloads

Downloads (Last 12 months)2
Downloads (Last 6 weeks)0

Reflects downloads up to 02 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Liu CLiao XZheng LHuang YLiu HZhang YHe HHuang HZhou JJin H(2024)L-FNNG: Accelerating Large-Scale KNN Graph Construction on CPU-FPGA Heterogeneous PlatformACM Transactions on Reconfigurable Technology and Systems10.1145/365260917:3(1-29)Online publication date: 14-Mar-2024
https://dl.acm.org/doi/10.1145/3652609
Liu CLiu HZheng LHuang YYe XLiao XJin HIenne PZhang Z(2023)FNNG: A High-Performance FPGA-based Accelerator for K-Nearest Neighbor Graph ConstructionProceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays10.1145/3543622.3573189(67-77)Online publication date: 12-Feb-2023
https://dl.acm.org/doi/10.1145/3543622.3573189
Wu XLiu SBai Y(2023)The manifold regularized SVDD for noisy label detectionInformation Sciences: an International Journal10.1016/j.ins.2022.10.109619:C(235-248)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1016/j.ins.2022.10.109
Muñoz JDias ZTorres R(2022)A genetic programming approach for searching on nearest neighbors graphsMultimedia Tools and Applications10.1007/s11042-022-12248-w81:16(23449-23472)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.1007/s11042-022-12248-w
Wang HZhao WZeng XYang JDemartini GZuccon GCulpepper JHuang ZTong H(2021)Fast k-NN Graph Construction by GPU based NN-DescentProceedings of the 30th ACM International Conference on Information & Knowledge Management10.1145/3459637.3482344(1929-1938)Online publication date: 26-Oct-2021
https://dl.acm.org/doi/10.1145/3459637.3482344
Magliani FPrati A(2021)LSH kNN graph for diffusion on image retrievalInformation Retrieval Journal10.1007/s10791-020-09388-8Online publication date: 7-Jan-2021
https://doi.org/10.1007/s10791-020-09388-8
Magliani FMcGuinness KMohedano EPrati A(2019)An Efficient Approximate kNN Graph Method for Diffusion on Image RetrievalImage Analysis and Processing – ICIAP 201910.1007/978-3-030-30645-8_49(537-548)Online publication date: 9-Sep-2019
https://dl.acm.org/doi/10.1007/978-3-030-30645-8_49
Bratić BHoule MKurbalija VOria VRadovanović M(2018)NN-Descent on High-Dimensional DataProceedings of the 8th International Conference on Web Intelligence, Mining and Semantics10.1145/3227609.3227643(1-8)Online publication date: 25-Jun-2018
https://dl.acm.org/doi/10.1145/3227609.3227643
Houle MMa XOria VSun J(2017)Query Expansion for Content-Based Similarity Search Using Local and Global FeaturesACM Transactions on Multimedia Computing, Communications, and Applications10.1145/306359513:3(1-23)Online publication date: 31-May-2017
https://dl.acm.org/doi/10.1145/3063595
Rao VJain PJawahar CKender JSmith JLuo JBoll SHsu W(2016)Diverse Yet Efficient Retrieval using Locality Sensitive HashingProceedings of the 2016 ACM on International Conference on Multimedia Retrieval10.1145/2911996.2911998(189-196)Online publication date: 6-Jun-2016
https://dl.acm.org/doi/10.1145/2911996.2911998
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten