# Revisiting Winner Take All (WTA) Hashing for Sparse Datasets

Source: [Revisiting Winner Take All (WTA) Hashing for Sparse Datasets](<https://www.sota2.com/research/paper/68fa62fe1e209131ce9fc1e2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:30:18.740Z

Authors: Beidi Chen, Anshumali Shrivastava

Published: 2016-12-06T14:51:37.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1612.01834>)

[PDF](<https://arxiv.org/pdf/1612.01834.pdf>)