|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ФИЦ ПХФ и МХ РАН |
||
ReMix: Training Generalized Person Re-identification on a Mixture of Dataстатья
- Авторы: Mamedov Timur, Konushin Anton, Konushin Vadim
- Сборник: Proceedings of the Winter Conference on Applications of Computer Vision (WACV)
- Год издания: 2025
- Место издания: IEEE
- Первая страница: 8175
- Последняя страница: 8185
- DOI: 10.1109/WACV61041.2025.00794
- Аннотация: Modern person re-identification (Re-ID) methods have a weak generalization ability and experience a major accuracy drop when capturing environments change. This is because existing multi-camera Re-ID datasets are limited in size and diversity since such data is difficult to obtain. At the same time enormous volumes of unlabeled single-camera records are available. Such data can be easily collected and therefore it is more diverse. Currently single-camera data is used only for self-supervised pre-training of Re-ID methods. However the diversity of single-camera data is suppressed by fine-tuning on limited multi-camera data after pre-training. In this paper we propose ReMix a generalized Re-ID method jointly trained on a mixture of limited labeled multi-camera and large unlabeled single-camera data. Effective training of our method is achieved through a novel data sampling strategy and new loss functions that are adapted for joint use with both types of data. Experiments show that ReMix has a high generalization ability and outperforms state-of-the-art methods in generalizable person Re-ID. To the best of our knowledge this is the first work that explores joint training on a mixture of multi-camera and single-camera data in person Re-ID.
- Добавил в систему: Мамедов Тимур Закирович