Progressive Learning Algorithm for Efficient Person Re-Identification

12/16/2019
by   Zhen Li, et al.
13

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.

READ FULL TEXT
research
12/17/2018

Learning Incremental Triplet Margin for Person Re-identification

Person re-identification (ReID) aims to match people across multiple non...
research
03/17/2020

Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning

This work considers the problem of domain shift in person re-identificat...
research
11/24/2020

DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations

Existing person re-identification methods often have low generalization ...
research
12/07/2018

Optimizing Speed/Accuracy Trade-Off for Person Re-identification via Knowledge Distillation

Finding a person across a camera network plays an important role in vide...
research
03/29/2018

Adversarial Binary Coding for Efficient Person Re-identification

Person re-identification (ReID) aims at matching persons across differen...
research
09/04/2020

Class Interference Regularization

Contrastive losses yield state-of-the-art performance for person re-iden...
research
05/08/2018

Efficient online learning for large-scale peptide identification

Motivation: Post-database searching is a key procedure in peptide dentif...

Please sign up or login with your details

Forgot password? Click here to reset