Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 3723 - 3732
• Main Authors: Saito, Kuniaki, Watanabe, Kohei, Ushiku, Yoshitaka, Harada, Tatsuya
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Feature extraction; Generators; Learning systems; Neural networks; Semantics; Task analysis; Training

In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the discriminator. Two problems exist with these methods. F...