Population-Based Evolutionary Gaming for Unsupervised Person Re-identification
Preprint
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 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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Cluster Contrast for Unsupervised Person Re-identification2023
- Multiple Expert Brainstorming for Domain Adaptive Person Re-Identification2020
- Global Distance-Distributions Separation for Unsupervised Person Re-identification2020
- Unsupervised domain adaptive re-identification: Theory and practicePattern Recognition, 2020
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- Generalizing a Person Retrieval Model Hetero- and Homogeneously2018
- Re-ranking Person Re-identification with k-Reciprocal Encoding2017
- Performance Measures and a Data Set for Multi-target, Multi-camera Tracking2016
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated ClustersJournal of Cybernetics, 1973