Source-Guided Similarity Preservation for Online Person Re-Identification

arXiv:2402.15206v1 Announce Type: new
Abstract: Online Unsupervised Domain Adaptation (OUDA) for person Re-Identification (Re-ID) is the task of continuously adapting a model trained on a well-annotated source domain dataset to a target domain observed as a data stream. In OUDA, person Re-ID models face two main challenges: catastrophic forgetting and domain shift. In this work, we propose a new Source-guided Similarity Preservation (S2P) framework to alleviate these two problems. Our framework is based on the extraction of a support set …

abstract arxiv catastrophic forgetting challenges cs.cv data dataset data stream domain domain adaptation face identification person preservation shift type unsupervised