AttributeNet: Attribute enhanced vehicle re-identification

Autor(es)

Quispe, Rodolfo ^{[1, 2]} ; Lan, Cuiling ^[3] ; Zeng, Wenjun ^[3] ; Pedrini, Helio ^[1]

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Inst Comp, BR-13083852 Campinas - Brazil

^[2] Microsoft Corp, One Microsoft Way, Redmond, WA 98052 - USA

^[3] Microsoft Res Asia, Beijing 100080 - Peoples R China

• Tipo de documento: Artigo Científico
• Fonte: Neurocomputing; v. 465, p. 84-92, NOV 20 2021.
• Citações Web of Science: 0

Resumo

Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints. Many works explore attribute clues to enhance V-ReID; however, there is usually a lack of effective interaction between the attribute-related modules and final V-ReID objective. In this work, we propose a new method to efficiently explore discriminative information from vehicle attributes (for instance, color and type). We introduce AttributeNet (ANet) that jointly extracts identity-relevant features and attribute features. We enable the interaction by distilling the ReIDhelpful attribute feature and adding it into the general ReID feature to increase the discrimination power. Moreover, we propose a constraint, named Amelioration Constraint (AC), which encourages the feature after adding attribute features onto the general ReID feature to be more discriminative than the original general ReID feature. We validate the effectiveness of our framework on three challenging datasets. Experimental results show that our method achieves the state-of-the-art performance . (c) 2021 Elsevier B.V. All rights reserved. (AU)

• Processo FAPESP: 17/12646-3 - Déjà vu: coerência temporal, espacial e de caracterização de dados heterogêneos para análise e interpretação de integridade
• Beneficiário: Anderson de Rezende Rocha
• Modalidade de apoio: Auxílio à Pesquisa - Temático