Generate and Purify: Efficient Person Data Generation for Re-Identification

Generating person images has been a promising approach to enhance the input richness for re-identification (reID) tasks in recent works. A key challenge is that the generated data often contains noise, which is caused by identity inconsistency between the generated person and the original input and...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2022, Vol.24, p.558-566
Main Authors: Lu, Jianjie, Zhang, Weidong, Yin, Haibing
Format: Article
Language:English
Subjects:
Convolutional codes
Data models
Generative adversarial networks
Graph clustering
Heating systems
Image enhancement
Image quality
Image synthesis
person generation
re-identification
Training
Training data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Generating person images has been a promising approach to enhance the input richness for re-identification (reID) tasks in recent works. A key challenge is that the generated data often contains noise, which is caused by identity inconsistency between the generated person and the original input and failure cases in generative adversarial networks (GAN). Directly training using generated images may greatly affect learning good feature embeddings, resulting in unsatisfactory reID performance. This work presents a two-stage framework that can generate high-quality person images and purify failure cases for reID training. Experimental results demonstrate that our proposed generative model can produce person images with superior appearance consistency comparing with other state-of-the-art methods. Furthermore, we show that our method yields a significant improvement in re-identification (reID) task on public datasets with insufficient training data.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2021.3054973