Unsupervised Domain Adaptation with Adversarial Residual Transform Networks
This work addresses domain adaptation challenges for machine learning applications where labeled data is scarce, but it is incremental, building on existing adversarial methods.
The paper tackles the problem of poor generalization and training difficulty in deep adversarial domain adaptation by proposing Adversarial Residual Transform Networks (ARTNs), which transform source features into target feature space using residual connections and a reconstructed adversarial loss, achieving performance comparable to state-of-the-art methods on datasets like Amazon reviews, digits, and Office-31.
Domain adaptation is widely used in learning problems lacking labels. Recent studies show that deep adversarial domain adaptation models can make markable improvements in performance, which include symmetric and asymmetric architectures. However, the former has poor generalization ability whereas the latter is very hard to train. In this paper, we propose a novel adversarial domain adaptation method named Adversarial Residual Transform Networks (ARTNs) to improve the generalization ability, which directly transforms the source features into the space of target features. In this model, residual connections are used to share features and adversarial loss is reconstructed, thus making the model more generalized and easier to train. Moreover, a special regularization term is added to the loss function to alleviate a vanishing gradient problem, which enables its training process stable. A series of experiments based on Amazon review dataset, digits datasets and Office-31 image datasets are conducted to show that the proposed ARTN can be comparable with the methods of the state-of-the-art.