January 2019
Intermediate to advanced
316 pages
8h 16m
English
The problem with only using adversarial loss is that the network can map the same set of input images to any random permutation of images in the target domain. Any of the learned mappings can, therefore, learn an output distribution that is similar to the target distribution. There can be many possible mapping functions between
and
. Cycle consistency loss overcomes this problem by reducing the number of possible mappings. A cycle consistent mapping function is a function that can translate an image x from domain A to ...
Read now
Unlock full access