Divide and Fuse: A Re-ranking Approach for Person Re-identification

TL;DR

This paper introduces a re-ranking framework for person re-identification that leverages feature division and fusion to improve accuracy without requiring multiple feature types, demonstrating superior results on benchmark datasets.

Contribution

The proposed 'Divide and use' re-ranking method innovatively exploits feature sub-divisions for fusion-based re-ranking, enhancing re-ID performance with a single feature type.

Findings

Outperforms state-of-the-art on Market-1501 dataset

Effective in utilizing feature diversity from high-dimensional vectors

Improves re-ranking accuracy without additional feature types

Abstract

As re-ranking is a necessary procedure to boost person re-identification (re-ID) performance on large-scale datasets, the diversity of feature becomes crucial to person reID for its importance both on designing pedestrian descriptions and re-ranking based on feature fusion. However, in many circumstances, only one type of pedestrian feature is available. In this paper, we propose a "Divide and use" re-ranking framework for person re-ID. It exploits the diversity from different parts of a high-dimensional feature vector for fusion-based re-ranking, while no other features are accessible. Specifically, given an image, the extracted feature is divided into sub-features. Then the contextual information of each sub-feature is iteratively encoded into a new feature. Finally, the new features from the same image are fused into one vector for re-ranking. Experimental results on two person re-ID benchmarks demonstrate the effectiveness of the proposed framework. Especially, our method outperforms the state-of-the-art on the Market-1501 dataset.