Quiet: Faster belief propagation for images and related applications

Yasuhiro Fujiwara, Dennis Shasha

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Belief propagation over Markov random fields has been successfully used in many AI applications since it yields accurate inference results by iteratively updating messages between nodes. However, its high computation costs are a barrier to practical use. This paper presents an efficient approach to belief propagation. Our approach, Quiet, dynamically detects converged messages to skip unnecessary updates in each iteration while it theoretically guarantees to output the same results as the standard approach used to implement belief propagation. Experiments show that our approach is significantly faster than existing approaches without sacrificing inference quality.

Original languageEnglish (US)
Title of host publicationIJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3497-3503
Number of pages7
Volume2015-January
ISBN (Print)9781577357384
StatePublished - 2015
Event24th International Joint Conference on Artificial Intelligence, IJCAI 2015 - Buenos Aires, Argentina
Duration: Jul 25 2015Jul 31 2015

Other

Other24th International Joint Conference on Artificial Intelligence, IJCAI 2015
CountryArgentina
CityBuenos Aires
Period7/25/157/31/15

Fingerprint

Costs
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Fujiwara, Y., & Shasha, D. (2015). Quiet: Faster belief propagation for images and related applications. In IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence (Vol. 2015-January, pp. 3497-3503). International Joint Conferences on Artificial Intelligence.

Quiet : Faster belief propagation for images and related applications. / Fujiwara, Yasuhiro; Shasha, Dennis.

IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence. Vol. 2015-January International Joint Conferences on Artificial Intelligence, 2015. p. 3497-3503.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fujiwara, Y & Shasha, D 2015, Quiet: Faster belief propagation for images and related applications. in IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence. vol. 2015-January, International Joint Conferences on Artificial Intelligence, pp. 3497-3503, 24th International Joint Conference on Artificial Intelligence, IJCAI 2015, Buenos Aires, Argentina, 7/25/15.
Fujiwara Y, Shasha D. Quiet: Faster belief propagation for images and related applications. In IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence. Vol. 2015-January. International Joint Conferences on Artificial Intelligence. 2015. p. 3497-3503
Fujiwara, Yasuhiro ; Shasha, Dennis. / Quiet : Faster belief propagation for images and related applications. IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence. Vol. 2015-January International Joint Conferences on Artificial Intelligence, 2015. pp. 3497-3503
@inproceedings{571cd7960002484c8ee493538957ddcc,
title = "Quiet: Faster belief propagation for images and related applications",
abstract = "Belief propagation over Markov random fields has been successfully used in many AI applications since it yields accurate inference results by iteratively updating messages between nodes. However, its high computation costs are a barrier to practical use. This paper presents an efficient approach to belief propagation. Our approach, Quiet, dynamically detects converged messages to skip unnecessary updates in each iteration while it theoretically guarantees to output the same results as the standard approach used to implement belief propagation. Experiments show that our approach is significantly faster than existing approaches without sacrificing inference quality.",
author = "Yasuhiro Fujiwara and Dennis Shasha",
year = "2015",
language = "English (US)",
isbn = "9781577357384",
volume = "2015-January",
pages = "3497--3503",
booktitle = "IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",

}

TY - GEN

T1 - Quiet

T2 - Faster belief propagation for images and related applications

AU - Fujiwara, Yasuhiro

AU - Shasha, Dennis

PY - 2015

Y1 - 2015

N2 - Belief propagation over Markov random fields has been successfully used in many AI applications since it yields accurate inference results by iteratively updating messages between nodes. However, its high computation costs are a barrier to practical use. This paper presents an efficient approach to belief propagation. Our approach, Quiet, dynamically detects converged messages to skip unnecessary updates in each iteration while it theoretically guarantees to output the same results as the standard approach used to implement belief propagation. Experiments show that our approach is significantly faster than existing approaches without sacrificing inference quality.

AB - Belief propagation over Markov random fields has been successfully used in many AI applications since it yields accurate inference results by iteratively updating messages between nodes. However, its high computation costs are a barrier to practical use. This paper presents an efficient approach to belief propagation. Our approach, Quiet, dynamically detects converged messages to skip unnecessary updates in each iteration while it theoretically guarantees to output the same results as the standard approach used to implement belief propagation. Experiments show that our approach is significantly faster than existing approaches without sacrificing inference quality.

UR - http://www.scopus.com/inward/record.url?scp=84949771379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949771379&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84949771379

SN - 9781577357384

VL - 2015-January

SP - 3497

EP - 3503

BT - IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence

PB - International Joint Conferences on Artificial Intelligence

ER -