On the relationship between visual attributes and convolutional networks

Victor Escorcia, Juan Carlos Niebles, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

66 Scopus citations

Abstract

One of the cornerstone principles of deep models is their abstraction capacity, i.e. their ability to learn abstract concepts from 'simpler' ones. Through extensive experiments, we characterize the nature of the relationship between abstract concepts (specifically objects in images) learned by popular and high performing convolutional networks (conv-nets) and established mid-level representations used in computer vision (specifically semantic visual attributes). We focus on attributes due to their impact on several applications, such as object description, retrieval and mining, and active (and zero-shot) learning. Among the findings we uncover, we show empirical evidence of the existence of Attribute Centric Nodes (ACNs) within a conv-net, which is trained to recognize objects (not attributes) in images. These special conv-net nodes (1) collectively encode information pertinent to visual attribute representation and discrimination, (2) are unevenly and sparsely distribution across all layers of the conv-net, and (3) play an important role in conv-net based object recognition.

Original languageEnglish (US)
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages1256-1264
Number of pages9
ISBN (Electronic)9781467369640
DOIs
StatePublished - Oct 14 2015
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: Jun 7 2015Jun 12 2015

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume07-12-June-2015
ISSN (Print)1063-6919

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/TerritoryUnited States
CityBoston
Period06/7/1506/12/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'On the relationship between visual attributes and convolutional networks'. Together they form a unique fingerprint.

Cite this