OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

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.

Authors

• Junjie Wang School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen International Research Institute for Artificial Intelligence, Harbin Institute of Technology, Shenzhen
• Bin Chen Harbin Institute of Technology, Shenzhen Research Center of Artificial Intelligence, Peng Cheng Laboratory
• Bin Kang School of Computer Science and Technology, University of the Chinese Academy of Sciences
• Yulin Li School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen International Research Institute for Artificial Intelligence, Harbin Institute of Technology, Shenzhen
• Weizhi Xian Chongqing Research Institute of HIT
• Yichi Chen School of Computer Science and Technology, University of the Chinese Academy of Sciences
• Yong Xu

Keywords

No keywords are indexed for this paper.