Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection
IEEE Transactions on Circuits and Systems for Video Technology · 2026-01 · 36 (1) · 106-118
DOI: 10.1109/tcsvt.2025.3596089 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-01. Verfasst von Hao Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Tianjin Municipality, Beijing Postdoctoral Research Foundation.
Abstract (Originalsprache)
Single-domain generalized object detection aims to enhance a model’s generalization to multiple unseen target domains using only data from a single source domain during training. This is a practical yet challenging scenario, as it requires the model to address domain shift without incorporating target domain data into the training process. In this paper, we propose a novel phrase-grounding-based style transfer (PGST) approach for the task. Specifically, we first define textual prompts to describe objects for potential unseen target domains. Then, we leverage the grounded language-image pre-training (GLIP) model to capture the styles of these target domains and perform style transfer from the source to the target domains. The style-transferred visual features from the source domain are semantically rich and closely approximate those of their hypothetical counterparts in the target domain. Finally, we employ these style-transferred visual features to fine-tune GLIP. By introducing these imaginary counterparts, the detector can be effectively generalized to unseen target domains using only a single source domain during training. Our method significantly improves mean average precision (mAP), with an average increase of 8.8% across five diverse weather-driving benchmarks. Notably, our approach outperforms or matches the performance of domain-adaptive object detection methods, which require target domain data for training, in several challenging scenarios.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Tianjin Municipality
- Beijing Postdoctoral Research Foundation
Zitieren
APA
Li, H., Wang, W., Wang, C., Wang, M., Zhang, X., Lan, L., Liu, X., Li, K., & Cao, X. (2026). Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(1), 106-118. https://doi.org/10.1109/tcsvt.2025.3596089
Vancouver
Li H, Wang W, Wang C, Wang M, Zhang X, Lan L, et al. Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(1):106-118. doi:10.1109/tcsvt.2025.3596089
BibTeX
@article{Li2026,
author = {Li, Hao and Wang, Wei and Wang, Cong and Wang, Mengzhu and Zhang, Xiang and Lan, Long and Liu, Xinwang and Li, Kenli and Cao, Xiaochun},
title = {Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {1},
pages = {106--118},
doi = {10.1109/tcsvt.2025.3596089}
}
EUVIMED