Posts /

Domain Adversarial Training of Neural Networks

Twitter Facebook
09 Aug 2017

Learning a discriminative classifier or other predictor in the presence of a shift between training and test distributions is known as domain adaptation(DA).

the appeal of the domain adaptation approaches is the ability to learn a mapping between domains in the situation when the target domain are either fully unlabeled (unsupervised domain annotation) or have few labeled samples(semi-supervised domain adaptation).


Twitter Facebook