Apparatus and method for unsupervised domain adaptation

Abstract

An apparatus is for unsupervised domain adaptation for allowing a deep learning model with supervised learning on a source domain completed to be subjected to unsupervised domain adaptation to a target domain. The apparatus includes a first learning unit to perform a forward pass by inputting a pair (x, y) of first data xof the source domain and a label yfor each of the first data and second data xbelonging to the target domain, and insert a dropout following a Bernoulli distribution into the deep learning model in performing the forward pass, and a second learning unit to perform a back propagation to minimize uncertainty about the learning parameter of the deep learning model by using a predicted value for each class output through the forward pass and the label y, and an uncertainty vector for the second data xoutput through the forward pass as inputs.