Hierarchical Cross Network for Person Re-identification

TL;DR

This paper introduces a Hierarchical Cross Network (HCN) architecture for person re-identification, which merges multi-resolution features to improve semantic understanding and enhances generalization through dataset augmentation, outperforming existing methods.

Contribution

The paper proposes a novel HCN architecture that merges multi-resolution features with hierarchical cross maps for improved person re-ID performance.

Findings

HCN outperforms several state-of-the-art methods.

Hierarchical cross feature maps uncover additional semantic features.

Data augmentation with multiple datasets improves generalization.

Abstract

Person re-identification (person re-ID) aims at matching target person(s) grabbed from different and non-overlapping camera views. It plays an important role for public safety and has application in various tasks such as, human retrieval, human tracking, and activity analysis. In this paper, we propose a new network architecture called Hierarchical Cross Network (HCN) to perform person re-ID. In addition to the backbone model of a conventional CNN, HCN is equipped with two additional maps called hierarchical cross feature maps. The maps of an HCN are formed by merging layers with different resolutions and semantic levels. With the hierarchical cross feature maps, an HCN can effectively uncover additional semantic features which could not be discovered by a conventional CNN. Although the proposed HCN can discover features with higher semantics, its representation power is still limited. To derive more general representations, we augment the data during the training process by combining multiple datasets. Experiment results show that the proposed method outperformed several state-of-the-art methods.