Ranking And Classification Driven Feature Learning For Person Re_identification

Abstract

Person re-identification has attracted many researchers' attention for its wide application, but it is still a very challenging task because only part of the image information can be used for personnel matching. Most of current methods uses CNN to learn to embeddings that can capture semantic similarity information among data points. Many of the state-of-the-arts methods use complex network structures with multiple branches that fuse multiple features while training or testing, using classification loss, Triplet loss or a combination of the two as loss function. However, the method that using Triplet loss as loss function converges slowly, and the method in which pull features of the same class as close as possible in features space leads to poor feature stability. This paper will combine the ranking motivated structured loss, proposed a new metric learning loss function that make the features of the same class are sparsely distributed into the range of small hyperspheres and the featu

Stats

• citations0
• S2 citations—
• github stars100
• HF likes0
• heat score4.01
• arxiv keyzhang2019ranking

Related papers

• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26
• Maskreid: A Mask Based Deep Ranking Neural Network For Person Re-identification (2018)0.00
• Person Re-identification Via Generalized Class Prototypes (2025)0.00