Re-identify people online by finding source images similar to the target with S2P
Re-identify people online by finding source images similar to the target with S2P
Source-Guided Similarity Preservation for Online Person Re-Identification
arXiv paper abstract https://arxiv.org/abs/2402.15206
arXiv PDF paper https://arxiv.org/pdf/2402.15206.pdf
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.
... propose a new Source-guided Similarity Preservation (S2P) framework to alleviate these two problems.
... based on the extraction of a support set composed of source images that maximizes the similarity with the target data.
This support set is used to identify feature similarities that must be preserved during the learning process.
... S2P outperforms previous state-of-the-art methods on multiple real-to-real and synthetic-to-real challenging OUDA benchmarks.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments