1

I found this answers. But, I don't get fully. If I have three labels in multi label classification task, did BCE produce 3 separate outputs? Why we shouldn't use CCE?

In this Facebook work they claim that, despite being counter-intuitive, Categorical Cross-Entropy loss, or Softmax loss worked better than Binary Cross-Entropy loss in their multi-label classification problem.

1chimaruGin
  • 11
  • 3
  • The paper you cite is about a special case of weakly supervised training, not a typical classification problem where samples taking on multiple labels. – Sycorax Feb 01 '21 at 02:33

0 Answers0