Discriminative Adversarial Domain Adaptation
This addresses domain adaptation challenges for machine learning applications where labeled data is scarce in target domains, representing an incremental improvement over existing adversarial methods.
The paper tackles the problem of mode collapse in unsupervised domain adaptation by proposing Discriminative Adversarial Domain Adaptation (DADA), which uses an integrated classifier to align joint distributions and achieves state-of-the-art results on benchmark datasets for closed, partial, and open set settings.
Given labeled instances on a source domain and unlabeled ones on a target domain, unsupervised domain adaptation aims to learn a task classifier that can well classify target instances. Recent advances rely on domain-adversarial training of deep networks to learn domain-invariant features. However, due to an issue of mode collapse induced by the separate design of task and domain classifiers, these methods are limited in aligning the joint distributions of feature and category across domains. To overcome it, we propose a novel adversarial learning method termed Discriminative Adversarial Domain Adaptation (DADA). Based on an integrated category and domain classifier, DADA has a novel adversarial objective that encourages a mutually inhibitory relation between category and domain predictions for any input instance. We show that under practical conditions, it defines a minimax game that can promote the joint distribution alignment. Except for the traditional closed set domain adaptation, we also extend DADA for extremely challenging problem settings of partial and open set domain adaptation. Experiments show the efficacy of our proposed methods and we achieve the new state of the art for all the three settings on benchmark datasets.