Result on coco position seems so bad

[XuankeShi]

Did you perform quantitative testing of this experiment on the COCO position? Is it possible that your results are severely overfitting on the LayoutSAM dataset, leading to a degradation in the generalization of the prompt?

[hrz2000]

Thank you very much for your interest in this work.

This is the data we used in training, which is mainly composed of the training set of LayoutSAM, which does perform better when prompted by similar distribution of LayoutSAM (such as natural scenery and real images)

I have tried to evaluate on GenEval, and I understand that it is very close to COCO, but the prompt is too simple and often "an apple and a banana", we have not seen much synthetic data like this in training, and the generalization here is really weak. More diverse data can mitigate this problem.

[quant1999]

Hi, I also get the similar question, could you let me know how to get the AP/AR score in the paper or provide any metrics code? @hrz2000