Context driven scene parsing with attention to rare classes

Jimei Yang, Brian Price, Scott Cohen, Ming Hsuan Yang

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

112 Citations (Scopus)

Abstract

This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching. We focus on rare object classes, which play an important role in achieving richer semantic understanding of visual scenes, compared to common background classes. Towards this end, we make two novel contributions: rare class expansion and semantic context description. First, considering the long-tailed nature of the label distribution, we expand the retrieval set by rare class exemplars and thus achieve more balanced superpixel classification results. Second, we incorporate both global and local semantic context information through a feedback based mechanism to refine image retrieval and superpixel matching. Results on the SIFTflow and LMSun datasets show the superior performance of our algorithm, especially on the rare classes, without sacrificing overall labeling accuracy.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages3294-3301
Number of pages8
ISBN (Electronic)9781479951178, 9781479951178
DOIs
Publication statusPublished - 2014 Sep 24
Event27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States
Duration: 2014 Jun 232014 Jun 28

Publication series

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

Other

Other27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
CountryUnited States
CityColumbus
Period14/6/2314/6/28

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Context driven scene parsing with attention to rare classes'. Together they form a unique fingerprint.

  • Cite this

    Yang, J., Price, B., Cohen, S., & Yang, M. H. (2014). Context driven scene parsing with attention to rare classes. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 3294-3301). [6909817] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.415