Search Results for author:
Found 2 papers, 2 papers with code
Towards Omni-supervised Referring Expression Segmentation
To address this issue, we propose a new learning task for RES called Omni-supervised Referring Expression Segmentation (Omni-RES), which aims to make full use of unlabeled, fully labeled and weakly labeled data, e. g., referring points or grounding boxes, for efficient RES training.
Towards Efficient Visual Adaption via Structural Re-parameterization
Experimental results show the superior performance and efficiency of RepAdapter than the state-of-the-art PETL methods.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
