OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
Junjie Wang, Bin Chen, Bin Kang, Yulin Li, Weizhi Xian, Yichi Chen, Yong Xu
Abstract
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.
BibTeX
@article{Wang_Chen_Kang_Li_Xian_Chen_Xu_2025, title={OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32836}, DOI={10.1609/aaai.v39i7.32836}, abstractNote={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.}, number={7}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Junjie and Chen, Bin and Kang, Bin and Li, Yulin and Xian, Weizhi and Chen, Yichi and Xu, Yong}, year={2025}, month={Apr.}, pages={7762-7770} }