Deep Metric Learning for Practical Person Re-Identification

07/18/2014
by   Dong Yi, et al.
0

Various hand-crafted features and metric learning methods prevail in the field of person re-identification. Compared to these methods, this paper proposes a more general way that can learn a similarity metric from image pixels directly. By using a "siamese" deep neural network, the proposed method can jointly learn the color feature, texture feature and metric in a unified framework. The network has a symmetry structure with two sub-networks which are connected by Cosine function. To deal with the big variations of person images, binomial deviance is used to evaluate the cost between similarities and labels, which is proved to be robust to outliers. Compared to existing researches, a more practical setting is studied in the experiments that is training and test on different datasets (cross dataset person re-identification). Both in "intra dataset" and "cross dataset" settings, the superiorities of the proposed method are illustrated on VIPeR and PRID.

READ FULL TEXT
research
10/09/2019

Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification

Person re-identification addresses the problem of matching pedestrian im...
research
08/16/2019

Learning Deep Representations by Mutual Information for Person Re-identification

Most existing person re-identification (ReID) methods have good feature ...
research
05/20/2018

A Deep Structure of Person Re-Identification using Multi-Level Gaussian Models

Person re-identification is being widely used in the forensic, and secur...
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
12/02/2018

Deep Cosine Metric Learning for Person Re-Identification

Metric learning aims to construct an embedding where two extracted featu...
research
11/18/2021

Robust Person Re-identification with Multi-Modal Joint Defence

The Person Re-identification (ReID) system based on metric learning has ...
research
11/27/2015

Structured learning of metric ensembles with application to person re-identification

Matching individuals across non-overlapping camera networks, known as pe...

Please sign up or login with your details

Forgot password? Click here to reset