OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (7) · 7762-7770
DOI: 10.1609/aaai.v39i7.32836 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Junjie Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref).
Abstract (Originalsprache)
Open-vocabulary detection aims to detect objects from novel categories beyond the base categories on which the detector is trained. However, existing open-vocabulary detectors trained on base category data tend to assign higher confidence to trained categories and confuse novel categories with the background. To resolve this, we propose OV-DQUO, an Open-Vocabulary DETR with Denoising text Query training and open-world Unknown Objects supervision. Specifically, we introduce a wildcard matching method. This method enables the detector to learn from pairs of unknown objects recognized by the open-world detector and text embeddings with general semantics, mitigating the confidence bias between base and novel categories. Additionally, we propose a denoising text query training strategy. It synthesizes foreground and background query-box pairs from open-world unknown objects to train the detector through contrastive learning, enhancing its ability to distinguish novel objects from the background. We conducted extensive experiments on the OV-COCO and OV-LVIS benchmarks, achieving new state-of-the-art results of 45.6 AP50 and 39.3 mAP on novel categories, respectively.
Zitieren
APA
Wang, J., Chen, B., Kang, B., Li, Y., Xian, W., Chen, Y., & Xu, Y. (2025). OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision. Proceedings of the AAAI Conference on Artificial Intelligence, 39(7), 7762-7770. https://doi.org/10.1609/aaai.v39i7.32836
Vancouver
Wang J, Chen B, Kang B, Li Y, Xian W, Chen Y, et al. OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(7):7762-7770. doi:10.1609/aaai.v39i7.32836
BibTeX
@article{Wang2025,
author = {Wang, Junjie and Chen, Bin and Kang, Bin and Li, Yulin and Xian, Weizhi and Chen, Yichi and Xu, Yong},
title = {OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {7},
pages = {7762--7770},
doi = {10.1609/aaai.v39i7.32836}
}
EUVIMED