munanning / mada Goto Github PK

As I understand, MADA need to generate a image-level featurte vector with the mean vector of all classes in a image. But if a category is missing in a picture(in fact it is a common phenomenon), how to generate the vector?

Hi!

Have you tested the method on any medical seg datasets? Thank you.

Appreciate this nicely presented paper.

As this is accepted as oral paper, I look for any video or slides as publication material to introduce this paper to my colleagues. Thank you!

Hello, I have some questions about Synthia training that I would like to ask you,

1. Is syhthia's warmup stage training conducted in 19 categories?
2. How many classes do you use in stage1 warmup? Is it 19 or 16?
   PS: can you share the model weight of Synthia dataset used by warmup? Thank you very much.

In your experiments, your method used DeepLab v3+ as the backbone to compare with other methods that use DeepLab v2, which is totally unfair. Can you report the results based on DeepLab v2?