Person re-identification based on Res2Net network

10/08/2019
by   Zongjing Cao, et al.
34

Person re-identification (re-ID) has been gaining in popularity in the research community owing to its numerous applications and growing importance in the surveillance industry. Person re-ID remains challenging due to significant intra-class variations across different cameras. In this paper, we propose a multi-task network that simultaneously computes the identification loss and verification loss. Given a pair of input images, the network predicts the identities of the two input images and whether they belong to the same identity. In order to obtain deeper feature information of pedestrians, we propose to use the latest Res2Net network for feature extraction. Experiments on several large-scale person re-ID benchmark datasets demonstrate the accuracy of our approach. For example, rank-1 accuracies are 82.67 (+0.21) for the DukeMTMC and Market-1501 datasets, respectively. The proposed method shows encouraging improvements compared with state-of-the-art methods.

READ FULL TEXT

page 2

page 3

page 4

research
11/17/2016

A Discriminatively Learned CNN Embedding for Person Re-identification

We revisit two popular convolutional neural networks (CNN) in person re-...
research
03/08/2021

Domain Adaptive Egocentric Person Re-identification

Person re-identification (re-ID) in first-person (egocentric) vision is ...
research
04/28/2021

Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification

In a real world environment, person re-identification (Re-ID) is a chall...
research
05/26/2021

Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification

As a prevailing task in video surveillance and forensics field, person r...
research
01/06/2021

HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification

Person Re-Identification (Re-ID) is of great importance to the many vide...
research
12/11/2020

A Multi-task Joint Framework for Real-time Person Search

Person search generally involves three important parts: person detection...
research
08/19/2020

Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification

Person re-identification (Re-ID) aims at retrieving an input person imag...

Please sign up or login with your details

Forgot password? Click here to reset