Person Re-identification Via Generalized Class Prototypes

Abstract

Advanced feature extraction methods have significantly contributed to enhancing the task of person re-identification. In addition, modifications to objective functions have been developed to further improve performance. Nonetheless, selecting better class representatives is an underexplored area of research that can also lead to advancements in re-identification performance. Although past works have experimented with using the centroid of a gallery image class during training, only a few have investigated alternative representations during the retrieval stage. In this paper, we demonstrate that these prior techniques yield suboptimal results in terms of re-identification metrics. To address the re-identification problem, we propose a generalized selection method that involves choosing representations that are not limited to class centroids. Our approach strikes a balance between accuracy and mean average precision, leading to improvements beyond the state of the art. For example, the a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymuzaddid2025person

Related papers

• Rethinking Person Re-identification From A Projection-on-prototypes Perspective (2023)0.00
• Person Re-identification: Past, Present And Future (2016)0.00
• Confidence-guided Centroids For Unsupervised Person Re-identification (2022)7.16
• Ranking And Classification Driven Feature Learning For Person Re_identification (2019)4.01
• Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26
• Neighbor-based Feature And Index Enhancement For Person Re-identification (2025)0.00
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• Specialized Re-ranking: A Novel Retrieval-verification Framework For Cloth Changing Person Re-identification (2022)9.03