Revisiting Winner Take All (WTA) Hashing for Sparse Datasets
Computer Vision and Pattern Recognition
2016-12-08 v2 Information Retrieval
Abstract
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 provably fixes the issue. Our experiments show that Densified WTA Hashing outperforms Vanilla WTA both in image classification and retrieval tasks consistently and significantly.
Keywords
Cite
@article{arxiv.1612.01834,
title = {Revisiting Winner Take All (WTA) Hashing for Sparse Datasets},
author = {Beidi Chen and Anshumali Shrivastava},
journal= {arXiv preprint arXiv:1612.01834},
year = {2016}
}