Progressive Learning Algorithm for Efficient Person Re-Identification

2019/12/16 by Li Zhen, Zhen Li, Hanyang Shao +9
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gait Recognition and Analysis #Human Pose and Action Recognition #Machine Learning (cs.LG) #Video Surveillance and Tracking Methods #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1912.07447

ICPR2020

openalex publication_date 2019/12/16 · arxiv created 2020/11/23 · arxiv updated 2020/11/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper studies the problem of Person Re-Identification (ReID)for large-scale applications. Recent research efforts have been devoted to building complicated part models, which introduce considerably high computational cost and memory consumption, inhibiting its practicability in large-scale applications. This paper aims to develop a novel learning strategy to find efficient feature embeddings while maintaining the balance of accuracy and model complexity. More specifically, we find by enhancing the classical triplet loss together with cross-entropy loss, our method can explore the hard examples and build a discriminant feature embedding yet compact enough for large-scale applications. Our method is carried out progressively using Bayesian optimization, and we call it the Progressive Learning Algorithm (PLA). Extensive experiments on three large-scale datasets show that our PLA is comparable or better than the-state-of-the-arts. Especially, on the challenging Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving at least 30% parameters than strong part models.

Citations

• Adam: A Method for Stochastic Optimization
• Practical Bayesian Optimization of Machine Learning Algorithms
• Taking the Human Out of the Loop: A Review of Bayesian Optimization
• Person Re-identification: Past, Present and Future
• In Defense of the Triplet Loss for Person Re-Identification
• Random Erasing Data Augmentation
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
• Re-ID done right: towards good practices for person re-identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression

Related

• Ranking and Classification driven Feature Learning for Person Re_identification
• Hierarchical and Efficient Learning for Person Re-Identification
• ReIDMamba: Learning Discriminative Features with Visual State Space Model for Person Re-Identification
• Incremental Learning in Person Re-Identification
• Highly Efficient Regression for Scalable Person Re-Identification