A Semi-supervised Maximum Margin Metric Learning Approach For Small Scale Person Re-identification

Abstract

In video surveillance, person re-identification is the task of searching person images in non-overlapping cameras. Though supervised methods for person re-identification have attained impressive performance, obtaining large scale cross-view labeled training data is very expensive. However, unlabelled data is available in abundance. In this paper, we propose a semi-supervised metric learning approach that can utilize information in unlabelled data with the help of a few labelled training samples. We also address the small sample size problem that inherently occurs due to the few labeled training data. Our method learns a discriminative space where within class samples collapse to singular points, achieving the least within class variance, and then use a maximum margin criterion over a high dimensional kernel space to maximally separate the distinct class samples. A maximum margin criterion with two levels of high dimensional mappings to kernel space is used to obtain better cross-view d

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyali2019a

Related papers

• Large Margin Learning In Set To Set Similarity Comparison For Person Re-identification (2017)12.10
• Cross-view Kernel Similarity Metric Learning Using Pairwise Constraints For Person Re-identification (2019)0.00
• Deep Cosine Metric Learning For Person Re-identification (2018)18.62
• Sparse Label Smoothing Regularization For Person Re-identification (2018)9.41
• Fully Unsupervised Person Re-identification Viaselective Contrastive Learning (2020)9.92
• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Ranking And Classification Driven Feature Learning For Person Re_identification (2019)4.01
• Confidence-guided Centroids For Unsupervised Person Re-identification (2022)7.16