Class Distribution Alignment for Adversarial Domain Adaptation
This work addresses domain adaptation for machine learning applications where class distribution mismatch hinders performance, offering an incremental improvement over existing methods.
The paper tackled the problem of unsupervised domain adaptation by aligning class distributions between source and target domains, rather than just marginal distributions, and achieved superior classification results on benchmark datasets like Digits, Faces, Scenes, and Office31 compared to state-of-the-art methods.
Most existing unsupervised domain adaptation methods mainly focused on aligning the marginal distributions of samples between the source and target domains. This setting does not sufficiently consider the class distribution information between the two domains, which could adversely affect the reduction of domain gap. To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains. It integrates a discriminative structure-preserving loss and a joint adversarial generation loss. The former effectively prevents undesired label-flipping during the whole process of image translation, while the latter maintains the joint distribution alignment of images and labels. Furthermore, our approach enforces the classification consistence of target domain images before and after adaptation to aid the classifier training in both domains. Extensive experiments were conducted on multiple benchmark datasets including Digits, Faces, Scenes and Office31, showing that our approach achieved superior classification in the target domain when compared to the state-of-the-art methods. Also, both qualitative and quantitative results well supported our motivation that aligning the class distributions can indeed improve domain adaptation.