Divide and Conquer: Hybrid Pre-training for Person Search
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5224-5232
DOI: 10.1609/aaai.v38i6.28329 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yanling Tian und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref).
Abstract (Originalsprache)
Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pre-training for person search, which involves detecting and re-identifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community (https://github.com/personsearch/PretrainPS).
Zitieren
APA
Tian, Y., Chen, D., Liu, Y., Yang, J., & Zhang, S. (2024). Divide and Conquer: Hybrid Pre-training for Person Search. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5224-5232. https://doi.org/10.1609/aaai.v38i6.28329
Vancouver
Tian Y, Chen D, Liu Y, Yang J, Zhang S. Divide and Conquer: Hybrid Pre-training for Person Search. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5224-5232. doi:10.1609/aaai.v38i6.28329
BibTeX
@article{Tian2024,
author = {Tian, Yanling and Chen, Di and Liu, Yunan and Yang, Jian and Zhang, Shanshan},
title = {Divide and Conquer: Hybrid Pre-training for Person Search},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {5224--5232},
doi = {10.1609/aaai.v38i6.28329}
}
EUVIMED