Dear author, I would like to ask you how to implement the qualitative analysis of the effectiveness of your global-local context visual features in the paper? Specifically , if we use COCO instance GT masks as mask proposals, how to predict the mask? Because I see that the final predicted mask in the code is selected from multiple mask proposals generated by freesolo, if we directly use GT mask as the mask proposal, then what is used to calculate the score?
Dear author, I would like to ask you how to implement the qualitative analysis of the effectiveness of your global-local context visual features in the paper? Specifically , if we use COCO instance GT masks as mask proposals, how to predict the mask? Because I see that the final predicted mask in the code is selected from multiple mask proposals generated by freesolo, if we directly use GT mask as the mask proposal, then what is used to calculate the score?