Conditional Adversarial Domain Adaptation
This work addresses domain adaptation for machine learning models, offering a principled framework that improves transferability and discriminability, though it is incremental in building on existing adversarial methods.
The paper tackles the problem of aligning multimodal distributions in domain adaptation by introducing conditional adversarial domain adaptation, which conditions adversarial models on classifier predictions, resulting in state-of-the-art performance on five datasets.
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal distributions native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. With theoretical guarantees and a few lines of codes, the approach has exceeded state-of-the-art results on five datasets.