Describing objects by their attributes

Ali Farhadi, Ian Endres, Derek W Hoiem, David Alexander Forsyth

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

Abstract

We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object ("spotty dog", not just "dog"); to say something about unfamiliar objects ("hairy and four-legged", not just "unknown"); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic ("spotty") or discriminative ("dogs have it but sheep do not"). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attributebased framework.

Original languageEnglish (US)
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PublisherIEEE Computer Society
Pages1778-1785
Number of pages8
ISBN (Print)9781424439935
DOIs
StatePublished - Jan 1 2009
Event2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Miami, FL, United States
Duration: Jun 20 2009Jun 25 2009

Publication series

Name2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
Volume2009 IEEE Computer Society Conference on Computer Vision and ...

Other

Other2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CountryUnited States
CityMiami, FL
Period6/20/096/25/09

Fingerprint

Feature extraction
Semantics

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Farhadi, A., Endres, I., Hoiem, D. W., & Forsyth, D. A. (2009). Describing objects by their attributes. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 (pp. 1778-1785). [5206772] (2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009; Vol. 2009 IEEE Computer Society Conference on Computer Vision and ...). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2009.5206772

Describing objects by their attributes. / Farhadi, Ali; Endres, Ian; Hoiem, Derek W; Forsyth, David Alexander.

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. IEEE Computer Society, 2009. p. 1778-1785 5206772 (2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009; Vol. 2009 IEEE Computer Society Conference on Computer Vision and ...).

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

Farhadi, A, Endres, I, Hoiem, DW & Forsyth, DA 2009, Describing objects by their attributes. in 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009., 5206772, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, vol. 2009 IEEE Computer Society Conference on Computer Vision and ..., IEEE Computer Society, pp. 1778-1785, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, FL, United States, 6/20/09. https://doi.org/10.1109/CVPRW.2009.5206772
Farhadi A, Endres I, Hoiem DW, Forsyth DA. Describing objects by their attributes. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. IEEE Computer Society. 2009. p. 1778-1785. 5206772. (2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009). https://doi.org/10.1109/CVPRW.2009.5206772
Farhadi, Ali ; Endres, Ian ; Hoiem, Derek W ; Forsyth, David Alexander. / Describing objects by their attributes. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. IEEE Computer Society, 2009. pp. 1778-1785 (2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009).
@inproceedings{dc6733bd052e4ab7b9ceab80cf878400,
title = "Describing objects by their attributes",
abstract = "We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object ({"}spotty dog{"}, not just {"}dog{"}); to say something about unfamiliar objects ({"}hairy and four-legged{"}, not just {"}unknown{"}); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic ({"}spotty{"}) or discriminative ({"}dogs have it but sheep do not{"}). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attributebased framework.",
author = "Ali Farhadi and Ian Endres and Hoiem, {Derek W} and Forsyth, {David Alexander}",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/CVPRW.2009.5206772",
language = "English (US)",
isbn = "9781424439935",
series = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009",
publisher = "IEEE Computer Society",
pages = "1778--1785",
booktitle = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009",

}

TY - GEN

T1 - Describing objects by their attributes

AU - Farhadi, Ali

AU - Endres, Ian

AU - Hoiem, Derek W

AU - Forsyth, David Alexander

PY - 2009/1/1

Y1 - 2009/1/1

N2 - We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object ("spotty dog", not just "dog"); to say something about unfamiliar objects ("hairy and four-legged", not just "unknown"); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic ("spotty") or discriminative ("dogs have it but sheep do not"). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attributebased framework.

AB - We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object ("spotty dog", not just "dog"); to say something about unfamiliar objects ("hairy and four-legged", not just "unknown"); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic ("spotty") or discriminative ("dogs have it but sheep do not"). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attributebased framework.

UR - http://www.scopus.com/inward/record.url?scp=70450207704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450207704&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2009.5206772

DO - 10.1109/CVPRW.2009.5206772

M3 - Conference contribution

AN - SCOPUS:70450207704

SN - 9781424439935

T3 - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

SP - 1778

EP - 1785

BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

PB - IEEE Computer Society

ER -