EUVIMEDEUVIMED entdecken
Crossref

Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection

Hao Li, Wei Wang, Cong Wang, Mengzhu Wang, Xiang Zhang, Long Lan, Xinwang Liu, Kenli Li, Xiaochun Cao

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →