PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification

06/05/2019
by   Chengyuan Zhang, et al.
0

Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based methods to enhance the recognition rate in a supervised or unsupervised manner. However, two limitations that cannot be ignored: firstly, compared with other image retrieval benchmarks, the size of existing person Re-Id datasets are far from meeting the requirement, which cannot provide sufficient pedestrian samples for the training of deep model; secondly, the samples in existing datasets do not have sufficient human motions or postures coverage to provide more priori knowledges for learning. In this paper, we introduce a novel unsupervised pose augmentation cross-view person Re-Id scheme called PAC-GAN to overcome these limitations. We firstly present the formal definition of cross-view pose augmentation and then propose the framework of PAC-GAN that is a novel conditional generative adversarial network (CGAN) based approach to improve the performance of unsupervised corss-view person Re-Id. Specifically, The pose generation model in PAC-GAN called CPG-Net is to generate enough quantity of pose-rich samples from original image and skeleton samples. The pose augmentation dataset is produced by combining the synthesized pose-rich samples with the original samples, which is fed into the corss-view person Re-Id model named Cross-GAN. Besides, we use weight-sharing strategy in the CPG-Net to improve the quality of new generated samples. To the best of our knowledge, we are the first try to enhance the unsupervised cross-view person Re-Id by pose augmentation, and the results of extensive experiments show that the proposed scheme can combat the state-of-the-arts.

READ FULL TEXT
research
12/06/2017

Pose-Normalized Image Generation for Person Re-identification

Person Re-identification (re-id) faces two major challenges: the lack of...
research
01/02/2023

Learning Invariance from Generated Variance for Unsupervised Person Re-identification

This work focuses on unsupervised representation learning in person re-i...
research
03/26/2017

Person Re-Identification by Camera Correlation Aware Feature Augmentation

The challenge of person re-identification (re-id) is to match individual...
research
08/23/2021

Exploring the Quality of GAN Generated Images for Person Re-Identification

Recently, GAN based method has demonstrated strong effectiveness in gene...
research
01/21/2018

Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification

Sufficient training data is normally required to train deeply learned mo...
research
01/04/2018

Crossing Generative Adversarial Networks for Cross-View Person Re-identification

Person re-identification (re-id) refers to matching pedestrians across d...
research
09/08/2021

Unsupervised clothing change adaptive person ReID

Clothing changes and lack of data labels are both crucial challenges in ...

Please sign up or login with your details

Forgot password? Click here to reset