Proposal Flow

Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce

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

38 Citations (Scopus)

Abstract

Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that proposal flow can effectively be transformed into a conventional dense flow field. We introduce a new dataset that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use this benchmark to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.

Original languageEnglish
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages3475-3484
Number of pages10
ISBN (Electronic)9781467388504
DOIs
Publication statusPublished - 2016 Dec 9
Event29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: 2016 Jun 262016 Jul 1

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2016-December
ISSN (Print)1063-6919

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period16/6/2616/7/1

Fingerprint

Semantics
Flow fields
Pixels
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Ham, B., Cho, M., Schmid, C., & Ponce, J. (2016). Proposal Flow. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 3475-3484). [7780747] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.378
Ham, Bumsub ; Cho, Minsu ; Schmid, Cordelia ; Ponce, Jean. / Proposal Flow. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. pp. 3475-3484 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{7589f2792d914e4990b5aaac1374d473,
title = "Proposal Flow",
abstract = "Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that proposal flow can effectively be transformed into a conventional dense flow field. We introduce a new dataset that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use this benchmark to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.",
author = "Bumsub Ham and Minsu Cho and Cordelia Schmid and Jean Ponce",
year = "2016",
month = "12",
day = "9",
doi = "10.1109/CVPR.2016.378",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "3475--3484",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
address = "United States",

}

Ham, B, Cho, M, Schmid, C & Ponce, J 2016, Proposal Flow. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780747, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 3475-3484, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.378

Proposal Flow. / Ham, Bumsub; Cho, Minsu; Schmid, Cordelia; Ponce, Jean.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 3475-3484 7780747 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

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

TY - GEN

T1 - Proposal Flow

AU - Ham, Bumsub

AU - Cho, Minsu

AU - Schmid, Cordelia

AU - Ponce, Jean

PY - 2016/12/9

Y1 - 2016/12/9

N2 - Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that proposal flow can effectively be transformed into a conventional dense flow field. We introduce a new dataset that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use this benchmark to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.

AB - Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that proposal flow can effectively be transformed into a conventional dense flow field. We introduce a new dataset that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use this benchmark to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.

UR - http://www.scopus.com/inward/record.url?scp=84986317342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986317342&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.378

DO - 10.1109/CVPR.2016.378

M3 - Conference contribution

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3475

EP - 3484

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -

Ham B, Cho M, Schmid C, Ponce J. Proposal Flow. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 3475-3484. 7780747. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2016.378