search

camel007 / caffe-moon

This repo is re-implement "MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes"
38 stars 16 forks source link

question of “MOON” and loss function. #10

Open chaipangpang opened 6 years ago

chaipangpang commented 6 years ago
  1. I do not find the mixed objective optimization，this project no relationship with the paper—“MOON”. 2.Why use the loss function —“EuclideanLoss”？It is better use “Sigmoid Cross-Entropy” or “HingeLoss”？
klintqinami commented 5 years ago

"Since CelebA has identical source and target distributions, we define the loss layer in (6) to weight all elements equally during backpropagation – which is equivalent to Euclidean loss between the network output and the 40 binary attribute values."

[Page 9, MOON : A Mixed Objective Optimization Network for the Recognition of Facial Attributes]