Back to Search
Start Over
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification.
- Source :
-
International Journal of Computer Vision . Jan2023, Vol. 131 Issue 1, p1-25. 25p. - Publication Year :
- 2023
-
Abstract
- 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 are 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. The code is released on github.com/YunpengZhai/PEG. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09205691
- Volume :
- 131
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- International Journal of Computer Vision
- Publication Type :
- Academic Journal
- Accession number :
- 161158844
- Full Text :
- https://doi.org/10.1007/s11263-022-01693-7