Graph Sampling Based Deep Metric Learning For Generalizable Person Re-identification

Abstract

Recent studies show that, both explicit deep feature matching as well as large-scale and diverse training data can significantly improve the generalization of person re-identification. However, the efficiency of learning deep matchers on large-scale data has not yet been adequately studied. Though learning with classification parameters or class memory is a popular way, it incurs large memory and computational costs. In contrast, pairwise deep metric learning within mini batches would be a better choice. However, the most popular random sampling method, the well-known PK sampler, is not informative and efficient for deep metric learning. Though online hard example mining has improved the learning efficiency to some extent, the mining in mini batches after random sampling is still limited. This inspires us to explore the use of hard example mining earlier, in the data sampling stage. To do so, in this paper, we propose an efficient mini-batch sampling method, called graph sampling (GS),

Stats

• citations114
• S2 citations—
• github stars218
• HF likes0
• heat score20.14
• arxiv keyliao2021graph

Related papers

• Dynamic Sampling For Deep Metric Learning (2020)5.84
• A Semi-supervised Maximum Margin Metric Learning Approach For Small Scale Person Re-identification (2019)4.52
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• Deep Cosine Metric Learning For Person Re-identification (2018)18.62
• Person Re-identification With Deep Similarity-guided Graph Neural Network (2018)17.55
• Person Re-identification Via Generalized Class Prototypes (2025)0.00
• Sparse Label Smoothing Regularization For Person Re-identification (2018)9.41
• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35