Rethinking Person Re-identification From A Projection-on-prototypes Perspective

Abstract

Person Re-IDentification (Re-ID) as a retrieval task, has achieved tremendous development over the past decade. Existing state-of-the-art methods follow an analogous framework to first extract features from the input images and then categorize them with a classifier. However, since there is no identity overlap between training and testing sets, the classifier is often discarded during inference. Only the extracted features are used for person retrieval via distance metrics. In this paper, we rethink the role of the classifier in person Re-ID, and advocate a new perspective to conceive the classifier as a projection from image features to class prototypes. These prototypes are exactly the learned parameters of the classifier. In this light, we describe the identity of input images as similarities to all prototypes, which are then utilized as more discriminative features to perform person Re-ID. We thereby propose a new baseline ProNet, which innovatively reserves the function of the cla

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2023rethinking

Related papers

• Person Re-identification Via Generalized Class Prototypes (2025)0.00
• Person Re-identification: Past, Present And Future (2016)0.00
• Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26
• Improving Person Re-identification By Attribute And Identity Learning (2017)20.71
• Specialized Re-ranking: A Novel Retrieval-verification Framework For Cloth Changing Person Re-identification (2022)9.03
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Confidence-guided Centroids For Unsupervised Person Re-identification (2022)7.16
• Instruct-reid++: Towards Universal Purpose Instruction-guided Person Re-identification (2024)9.13