Mixed High-Order Attention Network for Person Re-Identification

TL;DR

This paper introduces a novel high-order attention mechanism and a mixed high-order attention network to improve person re-identification by capturing subtle differences and complex statistics, outperforming existing methods.

Contribution

It proposes the High-Order Attention module and the MHN architecture, which incorporate complex statistical information for more discriminative attention in person ReID.

Findings

MHN outperforms state-of-the-art methods on three large-scale datasets.

High-Order Attention captures subtle differences among pedestrians.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Attention has become more attractive in person reidentification (ReID) as it is capable of biasing the allocation of available resources towards the most informative parts of an input signal. However, state-of-the-art works concentrate only on coarse or first-order attention design, e.g. spatial and channels attention, while rarely exploring higher-order attention mechanism. We take a step towards addressing this problem. In this paper, we first propose the High-Order Attention (HOA) module to model and utilize the complex and high-order statistics information in attention mechanism, so as to capture the subtle differences among pedestrians and to produce the discriminative attention proposals. Then, rethinking person ReID as a zero-shot learning problem, we propose the Mixed High-Order Attention Network (MHN) to further enhance the discrimination and richness of attention knowledge in an explicit manner. Extensive experiments have been conducted to validate the superiority of our MHN for person ReID over a wide variety of state-of-the-art methods on three large-scale datasets, including Market-1501, DukeMTMC-ReID and CUHK03-NP. Code is available at http://www.bhchen.cn/.