Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification. (arXiv:2205.06237v1 [cs.CV])

Web: http://arxiv.org/abs/2205.06237

Despite the recent success of deep learning architectures, person
re-identification (ReID) remains a challenging problem in real-word
applications. Several unsupervised single-target domain adaptation (STDA)
methods have recently been proposed to limit the decline in ReID accuracy
caused by the domain shift that typically occurs between source and target
video data. Given the multimodal nature of person ReID data (due to variations
across camera viewpoints and capture conditions), training a common CNN
backbone to address domain shifts across multiple target domains, …

arxiv cv distillation domain adaptation identification knowledge person real-time time