The implementation details of BlackVIP-SE

[yxizhong]

Dear authors,

Thank you for your work on Robust Adaptation of Foundation Models with Black-Box Visual Prompting, in which the method of PCA extraction of statistical information in BlackVIP-SE is a great inspiration to me. However, I encountered problems such as too large image size and image channel processing during the implementation, resulting in poor effect of mapping through PCA matrix. So want to refer to your practice in BlackVIP-SE, but can't seem to find it in this project? May I ask if the code implementation of PCA operation in BlackVIP-SE is in this project?

Thanks in advance.