search

kaixin96 / PANet

Code for our ICCV 2019 paper PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
321 stars 64 forks source link

How can generate the qualitative results as in your paper ? #11

Closed alex-marked closed 4 years ago

alex-marked commented 4 years ago

Hello, Thank you for your nice work. I am new in this area, my question is how can I obtain the qualitative results as in your paper Figure 3/4 ?

Thank you, Alex ~

kaixin96 commented 4 years ago

Hi @Alex-dong , you can train the model and test it on unseen images. The model will give you segmentation results. By overlaying the segmentation prediction with original images you can get figures like Figure 3/4.

alex-marked commented 4 years ago

OK Thanks for your reply, I will try. Best wishes ~

t-sh99 commented 1 year ago

Hi @alex-marked, have you successfully obtained the qualitative results on unseen images? How did you implement it? Thank you