Search Results for author:
Found 1 papers, 0 papers with code
HEAT: Head-level Parameter Efficient Adaptation of Vision Transformers with Taylor-expansion Importance Scores
In this paper, we propose Head-level Efficient Adaptation with Taylor-expansion importance score (HEAT): a simple method that efficiently fine-tuning ViTs at head levels.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
