Corpus ID: 2759146

Revisiting Winner Take All (WTA) Hashing for Sparse Datasets

@article{Chen2016RevisitingWT,
  title={Revisiting Winner Take All (WTA) Hashing for Sparse Datasets},
  author={Beidi Chen and Anshumali Shrivastava},
  journal={ArXiv},
  year={2016},
  volume={abs/1612.01834}
}
  • Beidi Chen, Anshumali Shrivastava
  • Published 2016
  • Computer Science
  • ArXiv
  • WTA (Winner Take All) hashing has been successfully applied in many large scale vision applications. This hashing scheme was tailored to take advantage of the comparative reasoning (or order based information), which showed significant accuracy improvements. In this paper, we identify a subtle issue with WTA, which grows with the sparsity of the datasets. This issue limits the discriminative power of WTA. We then propose a solution for this problem based on the idea of Densification which… CONTINUE READING

    Figures and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    Optimal Projection Guided Transfer Hashing for Image Retrieval

    VIEW 2 EXCERPTS
    CITES METHODS

    On Densification for Minwise Hashing

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES

    Improved Densification of One Permutation Hashing

    VIEW 3 EXCERPTS

    Relative attributes

    VIEW 3 EXCERPTS

    LabelMe: A Database and Web-Based Tool for Image Annotation

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Support vector machines for histogram-based image classification

    VIEW 1 EXCERPT