Abstract: Prompt learning has been recently introduced into the adaption of pre-trained vision-language models (VLMs) by tuning a set of trainable tokens to replace hand-crafted text templates.
A one-tailed test ... significance. Utilizing a one-tailed test can lead to more focused and relevant conclusions, but it should only be applied when opposite outcomes are not critical to the analysis ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback