DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception

Junjie Wang, Bin Chen, Yulin Li, Bin Kang, Yichi Chen, Zhuotao Tian. DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, June 11-15, 2025. pages 14824-14834, Computer Vision Foundation / IEEE, 2025. [doi]

@inproceedings{WangCLKCT25,
  title = {DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception},
  author = {Junjie Wang and Bin Chen and Yulin Li and Bin Kang and Yichi Chen and Zhuotao Tian},
  year = {2025},
  url = {https://openaccess.thecvf.com/content/CVPR2025/html/Wang_DeCLIP_Decoupled_Learning_for_Open-Vocabulary_Dense_Perception_CVPR_2025_paper.html},
  researchr = {https://researchr.org/publication/WangCLKCT25},
  cites = {0},
  citedby = {0},
  pages = {14824-14834},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, June 11-15, 2025},
  publisher = {Computer Vision Foundation / IEEE},
  isbn = {979-8-3503-5300-6},
}