SCIENCE@home

Fisher and VLAD with FLAIR

K. V. D. Sande,Cees G. M. Snoek,A. Smeulders

Published 2014 in 2014 IEEE Conference on Computer Vision and Pattern Recognition

ABSTRACT

A major computational bottleneck in many current algorithms is the evaluation of arbitrary boxes. Dense local analysis and powerful bag-of-word encodings, such as Fisher vectors and VLAD, lead to improved accuracy at the expense of increased computation time. Where a simplification in the representation is tempting, we exploit novel representations while maintaining accuracy. We start from state-of-the-art, fast selective search, but our method will apply to any initial box-partitioning. By representing the picture as sparse integral images, one per codeword, we achieve a Fast Local Area Independent Representation. FLAIR allows for very fast evaluation of any box encoding and still enables spatial pooling. In FLAIR we achieve exact VLAD's difference coding, even with L2 and power-norms. Finally, by multiple codeword assignments, we achieve exact and approximate Fisher vectors with FLAIR. The results are a 18x speedup, which enables us to set a new state-of-the-art on the challenging 2010 PASCAL VOC objects and the fine-grained categorization of the CUB-2011 200 bird species. Plus, we rank number one in the official ImageNet 2013 detection challenge.

PUBLICATION RECORD

  • Publication year

    2014

  • Venue

    2014 IEEE Conference on Computer Vision and Pattern Recognition

  • Publication date

    2014-06-01

  • Fields of study

    Computer Science

  • Identifiers
    DOI 10.1109/CVPR.2014.304
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-31 of 31 references · Page 1 of 1

CITED BY

Showing 1-71 of 71 citing papers · Page 1 of 1