On the Relationship between Visual Attributes and Convolutional Networks

Type
Conference Paper

Authors
Castillo, Victor
Ghanem,Bernard
Niebles, Juan Carlos

KAUST Department
Image and Video Understanding Lab

Online Publication Date
2015-10-15

Print Publication Date
2015-06

Date
2015-10-15

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.

Citation
Escorcia, V., Niebles, J. C., & Ghanem, B. (2015). On the relationship between visual attributes and convolutional networks. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr.2015.7298730

Acknowledgements
IEEE Computer Society, Computer Vision Foundation - CVF

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Journal
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

Conference/Event Name
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

DOI
10.1109/CVPR.2015.7298730

Additional Links
https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Escorcia_On_the_Relationship_2015_CVPR_paper.pdf

Permanent link to this record

Version History

Now showing 1 - 2 of 2
VersionDateSummary
2*
2018-05-09 11:42:01
Published with DOI
2015-06-02 13:29:58
* Selected version