An unsupervised domain adaptation model based on dual-module adversarial training

In this paper, we propose a dual-module network architecture that employs domain discriminative feature module to encourage the invariant learn more features. The proposed can be applied any model utilizes features for unsupervised adaptation improve its ability extract We conduct experiments with Domain-Adversarial Training of Neural Networks (DANN) as representative algorithm. training process, supply same input two modules and then their distribution prediction results respectively. discrepancy loss find between modules. Through adversarial by maximizing minimizing results, are encouraged Extensive comparative evaluations conducted approach outperforms state-of-the-art in most tasks.