csk1234
csk1234
Hello, are you saying that your current demo program can only implement the "point" prompt type? But I noticed that the paper involves the collaboration of multiple prompt types—does the...
Additionally, I would like to know if it is necessary to download the over 100,000 images from the LVIS training set for training purposes.
Hello, I have one more question. Do you have specific code for your text prompts? How are the text attributes obtained? For medical datasets where lesions are difficult to describe,...