Improving Adversarial Discriminative Domain Adaptation

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation, where the source and target domains are assumed to have the same classes, but no labels are available for the target domain. While ADDA has already achieved better training efficiency and competitive accuracy in comparison to other adversarial based methods, we investigate whether we can improve performance by incorporating task knowledge into the adversarial loss functions. We achieve this by extending the discriminator output over the source classes and leverage on the distribution over the source encoder posteriors, which is fixed during adversarial training, in order to align a shared encoder distribution to the source domain. The shared encoder can receive a proportion of examples from both the source and target datasets, in order to smooth the learned distribution and improve its convergence properties during adversarial training. We additionally consider how the extended discriminator can be regularized in order to further improve performance, by treating the discriminator as a denoising autoencoder and corrupting its input. Our final design employs maximum mean discrepancy and reconstruction-based loss functions for adversarial training. We validate our framework on standard datasets like MNIST, USPS, SVHN, MNIST-M and Office-31. Our results on all datasets show that our proposal is both simple and efficient, as it competes or outperforms the state-of-the-art in unsupervised domain adaptation, whilst offering lower complexity than other recent adversarial methods such as DIFA and CoGAN.