Dong ZHANG

hi, have you solved this problem ? I meet the same one, but i do not know how to do.

Thank you so much for your assistance, and I will try it.

Thanks, I will have a try.

I have the similar question.

@zjx103-orange No worry, the code is in preparation.

@coolbay Thanks, very good question. There are two main reasons why we do this: 1. The transformer itself is a very computationally intensive operation. It is not necessary to use...

Thanks for your attention. From my experience, it looks like that you did not initialize the segmentation model with the ImageNet pre-trained weight ? Besides, using the segmentation model trained...

@SunGuoYing The classification model and the segmentation model share the same backbone network. Using the segmentation weight in a new round classification is beneficial for generating CAMs.

@hiddlephila I just used the common pre-trained model in pytorch.

@pp00704831 LGT is used for semantic segmentation