Timezone: »

Conditional Adversarial Domain Adaptation
Mingsheng Long · ZHANGJIE CAO · Jianmin Wang · Michael Jordan

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #32

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may struggle to align different domains of multimodal distributions that are 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. Experiments testify that the proposed approach exceeds the state-of-the-art results on five benchmark datasets.

Author Information

Mingsheng Long (Tsinghua University)
ZHANGJIE CAO (Stanford University)
Jianmin Wang (Tsinghua University)
Michael Jordan (UC Berkeley)

More from the Same Authors