Universal source-free domain adaptation. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4544–4553, 2020. 5 [16] Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter-efficient prompt tuning. ar...
The model is trained on fully-supervised semantic segmentation datasets with pixel-level annotations (e.g., COCO Stuff dataset). Weakly-Supervised Open-Vocabulary Semantic Segmentation [text-supervised/language-supervised] The model is trained on weakly supervised datasets with only image-level annotation...