Unsupervised Domain Adaptation via Deep Conditional Adaptation Network

• A novel domain adaptation (DA) framework is proposed by aligning the conditional distributions and simultaneously extracting discriminant information from both domains. • Conditional Maximum Mean Discrepancy is used to align the conditional distributions directly by their conditional embeddings in Reproducing Kernel Hilbert Space. • We further extend the proposed DA framework on partial DA scenarios. • The proposed method achieves state-of-the-art performance on both DA and partial DA scenarios. Unsupervised domain adaptation (UDA) aims to generalize the supervised model trained on a source domain to an unlabeled target domain. Previous works mainly rely on the marginal distribution alignment of feature spaces, which ignore the conditional dependence between features and labels, and may suffer from negative transfer. To address this problem, some UDA methods focus on aligning the conditional distributions of feature spaces. However, most of these methods rely on class-specific Maximum Mean Discrepancy or adversarial training, which may suffer from mode collapse and training instability. In this paper, we propose a Deep Conditional Adaptation Network (DCAN) that aligns the conditional distributions by minimizing Conditional Maximum Mean Discrepancy, and extracts discriminant information from the target domain by maximizing the mutual information between samples and the prediction labels. Conditional Maximum Mean Discrepancy measures the difference between conditional distributions directly through their conditional embedding in Reproducing Kernel Hilbert Space, thus DCAN can be trained stably and converge fast. Mutual information can be expressed as the difference between the entropy and conditional entropy of the predicted category variable, thus DCAN can extract the discriminant information of individual and overall distributions in the target domain, simultaneously. In addition, DCAN can be used to address a special scenario, Partial UDA, where the target domain category is a subset of the source domain category. Experiments on both UDA and Partial UDA show that DCAN achieves superior classification performance over state-of-the-art methods.