Weiqiang Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weiqiang Chen has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Mengxi Jia
School of Software Microelectronics, Peking University, Beijing, China
2 shared publications - Peixi Peng
Peking University
2 shared publications - Shiyong Li
National Engineering Research Center of Visual Technology School of Computer Science Peking University China
2 shared publications - Xuesong Gao
Qingdao Hisense State Key Laboratory of Digital Multimedia Technology, QingDao, China
2 shared publications - Yonghong Tian
Peking University
2 shared publications - Yunpeng Zhai
School of Electronic and Computer Engineering Peking University China
2 shared publications
Latest Publications
- Open Access
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification
Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. However, limited by the lack of diversity of discriminant information, a single network has difficulty learning sufficient discrimination ability by itself under unsupervised conditions. To address this limit, we develop a population-based evolutionary gaming (PEG) framework in which a population of diverse neural networks is trained concurrently through selection, reproduction, mutation, and population mutual learning iteratively. Specifically, the selection of networks to preserve is modeled as a cooperative game and solved by the best-response dynamics, then the reproduction and mutation are implemented by cloning and fluctuating hyper-parameters of networks to learn more diversity, and population mutual learning improves the discrimination of networks by knowledge distillation from each other within the population. In addition, we propose a cross-reference scatter (CRS) to approximately evaluate re-ID models without labeled samples and adopt it as the criterion of network selection in PEG. CRS measures a model's performance by indirectly estimating the accuracy of its predicted pseudo-labels according to the cohesion and separation of the feature space. Extensive experiments demonstrate that (1) CRS approximately measures the performance of models without labeled samples; (2) and PEG produces new state-of-the-art accuracy for person re-identification, indicating the great potential of population-based network cooperative training for unsupervised learning.
Open AccessPopulation-Based Evolutionary Gaming for Unsupervised Person Re-identification
Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. However, limited by the lack of diversity of discriminant information, a single network has difficulty learning sufficient discrimination ability by itself under unsupervised conditions. To address this limit, we develop a population-based evolutionary gaming (PEG) framework in which a population of diverse neural networks is trained concurrently through selection, reproduction, mutation, and population mutual learning iteratively. Specifically, the selection of networks to preserve is modeled as a cooperative game and solved by the best-response dynamics, then the reproduction and mutation are implemented by cloning and fluctuating hyper-parameters of networks to learn more diversity, and population mutual learning improves the discrimination of networks by knowledge distillation from each other within the population. In addition, we propose a cross-reference scatter (CRS) to approximately evaluate re-ID models without labeled samples and adopt it as the criterion of network selection in PEG. CRS measures a model's performance by indirectly estimating the accuracy of its predicted pseudo-labels according to the cohesion and separation of the feature space. Extensive experiments demonstrate that (1) CRS approximately measures the performance of models without labeled samples; (2) and PEG produces new state-of-the-art accuracy for person re-identification, indicating the great potential of population-based network cooperative training for unsupervised learning.
- 1 October 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (1) , 1-25
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification
- 1 October 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (1) , 1-25
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification