Unlabeled data improves word prediction

Nicolas Loeff; Ali Farhadi; Ian Endres; David A. Forsyth

doi:10.1109/ICCV.2009.5459347

Unlabeled data improves word prediction

Nicolas Loeff, Ali Farhadi, Ian Endres, David A. Forsyth

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of the art models in word prediction to incorporate information from unlabeled examples, using manifold regularization. To the best of our knowledge this is the first semi-supervised multi-task model used in vision problems. The new model can be solved using gradient descent and is fast and efficient. We show remarkable improvements for cases with few labeled examples for challenging multi-task learning problems in vision (predicting words for images and attributes for objects).

Original language	English (US)
Title of host publication	2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
Pages	956-962
Number of pages	7
DOIs	https://doi.org/10.1109/ICCV.2009.5459347
State	Published - Dec 1 2009
Event	12th International Conference on Computer Vision, ICCV 2009 - Kyoto, Japan Duration: Sep 29 2009 → Oct 2 2009

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision

Other

Other	12th International Conference on Computer Vision, ICCV 2009
Country	Japan
City	Kyoto
Period	9/29/09 → 10/2/09

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2009.5459347

Fingerprint Dive into the research topics of 'Unlabeled data improves word prediction'. Together they form a unique fingerprint.

Cite this

Loeff, N., Farhadi, A., Endres, I., & Forsyth, D. A. (2009). Unlabeled data improves word prediction. In 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009 (pp. 956-962). [5459347] (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2009.5459347

Loeff, N, Farhadi, A, Endres, I & Forsyth, DA 2009, Unlabeled data improves word prediction. in 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009., 5459347, Proceedings of the IEEE International Conference on Computer Vision, pp. 956-962, 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, 9/29/09. https://doi.org/10.1109/ICCV.2009.5459347

@inproceedings{4c1522f410cc43f2b2d55043ecb54440,

title = "Unlabeled data improves word prediction",

abstract = "Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of the art models in word prediction to incorporate information from unlabeled examples, using manifold regularization. To the best of our knowledge this is the first semi-supervised multi-task model used in vision problems. The new model can be solved using gradient descent and is fast and efficient. We show remarkable improvements for cases with few labeled examples for challenging multi-task learning problems in vision (predicting words for images and attributes for objects).",

author = "Nicolas Loeff and Ali Farhadi and Ian Endres and Forsyth, {David A.}",

year = "2009",

month = dec,

day = "1",

doi = "10.1109/ICCV.2009.5459347",

language = "English (US)",

isbn = "9781424444205",

series = "Proceedings of the IEEE International Conference on Computer Vision",

pages = "956--962",

booktitle = "2009 IEEE 12th International Conference on Computer Vision, ICCV 2009",

note = "12th International Conference on Computer Vision, ICCV 2009 ; Conference date: 29-09-2009 Through 02-10-2009",

}

TY - GEN

T1 - Unlabeled data improves word prediction

AU - Loeff, Nicolas

AU - Farhadi, Ali

AU - Endres, Ian

AU - Forsyth, David A.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of the art models in word prediction to incorporate information from unlabeled examples, using manifold regularization. To the best of our knowledge this is the first semi-supervised multi-task model used in vision problems. The new model can be solved using gradient descent and is fast and efficient. We show remarkable improvements for cases with few labeled examples for challenging multi-task learning problems in vision (predicting words for images and attributes for objects).

AB - Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of the art models in word prediction to incorporate information from unlabeled examples, using manifold regularization. To the best of our knowledge this is the first semi-supervised multi-task model used in vision problems. The new model can be solved using gradient descent and is fast and efficient. We show remarkable improvements for cases with few labeled examples for challenging multi-task learning problems in vision (predicting words for images and attributes for objects).

UR - http://www.scopus.com/inward/record.url?scp=77953189631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953189631&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2009.5459347

DO - 10.1109/ICCV.2009.5459347

M3 - Conference contribution

AN - SCOPUS:77953189631

SN - 9781424444205

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 956

EP - 962

BT - 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009

T2 - 12th International Conference on Computer Vision, ICCV 2009

Y2 - 29 September 2009 through 2 October 2009

ER -