Details

Autor(en) / Beteiligte

• Wang, Pingyu
• Su, Fei
• Zhao, Zhicheng
• Zhao, Yanyun
• Boulgouris, Nikolaos V.

Titel

GAReID: Grouped and Attentive High-Order Representation Learning for Person Re-Identification

Ist Teil von

• IEEE transaction on neural networks and learning systems, 2022-10, Vol.PP, p.1-15

Ort / Verlag

United States: IEEE

Erscheinungsjahr

2022

Quelle

IEEE Electronic Library Online

Beschreibungen/Notizen

• As person parts are frequently misaligned between detected human boxes, an image representation that can handle this part misalignment is required. In this work, we propose an effective grouped attentive re-identification (GAReID) framework to learn part-aligned and background robust representations for person re-identification (ReID). Specifically, the GAReID framework consists of grouped high-order pooling (GHOP) and attentive high-order pooling (AHOP) layers, which generate high-order image and foreground features, respectively. In addition, a novel grouped Kronecker product (GKP) is proposed to use both channel group and shuffle strategies for high-order feature compression, while promoting the representational capabilities of compressed high-order features. We show that our method derives from an interpretable motivation and elegantly reduces part misalignments without using landmark detection or feature partition. This article theoretically and experimentally demonstrates the superiority of the GAReID framework, achieving state-of-the-art performance on various person ReID datasets.