kaixin96 / PANet

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

Align loss #48

Open Glutaredoxin opened 1 year ago

Glutaredoxin commented 1 year ago

Hi, thanks for your great works!!! In align_loss, i find for a certain sample, it is just a Binary classification problem [fore_ground and back_ground]. So...Maybe we can replace the cross_entropy for align_loss with the binary_loss??

please point out if my understanding is biased.

sorry to bother. :)