Re-ranking Person Re-identification with k-reciprocal Encoding

TL;DR

This paper introduces a fully automatic, unsupervised re-ranking method for person re-identification that leverages k-reciprocal encoding to improve retrieval accuracy by combining original and Jaccard distances.

Contribution

The paper proposes a novel k-reciprocal encoding approach for re-ranking in person re-ID, which is fully automatic and does not require labeled data.

Findings

Significant accuracy improvements on large-scale datasets

Effective in unsupervised, large-scale scenarios

Outperforms existing re-ranking methods

Abstract

When considering person re-identification (re-ID) as a retrieval process, re-ranking is a critical step to improve its accuracy. Yet in the re-ID community, limited effort has been devoted to re-ranking, especially those fully automatic, unsupervised solutions. In this paper, we propose a k-reciprocal encoding method to re-rank the re-ID results. Our hypothesis is that if a gallery image is similar to the probe in the k-reciprocal nearest neighbors, it is more likely to be a true match. Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance. The final distance is computed as the combination of the original distance and the Jaccard distance. Our re-ranking method does not require any human interaction or any labeled data, so it is applicable to large-scale datasets. Experiments on the large-scale Market-1501, CUHK03, MARS, and PRW datasets confirm the effectiveness of our method.