Personalized Re-identification through Unsupervised Continual Learning and Parallel Training

Abstract

Object re-identification and tracking lay the foundation for various computer vision and robotics applications. In this study, we propose a method for personalizing a neural network to enhance and continuously adapt the re-identification of a specific target. Employing an unsupervised continual learning approach in conjunction with an intelligent image pool collection, we can effectively track the target and mitigate the issue of catastrophic forgetting, a challenge prevalent in this research domain. Our primary goal is to provide a robust person re-identification approach to extend the capabilities of recent tracking frameworks employed in robotics, which we have adopted as our baselines for evaluation. Our results demonstrate our approach’s efficacy in successfully re-identifying the target, even when the target drastically changes his clothing appearance and the baseline frameworks struggle. To optimally tune the framework parameters, we conducted an ablation study and substantiated our findings with saliency maps to elucidate the reasons behind the effectiveness of our approach.