Deep Transfer Learning with Joint Adaptation Networks
This work addresses domain shift problems in machine learning, providing an incremental improvement over existing methods.
The paper tackles domain adaptation by aligning joint distributions of multiple layers across domains using joint maximum mean discrepancy and adversarial training, achieving state-of-the-art results on standard datasets.
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint adaptation networks (JAN), which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion. Adversarial training strategy is adopted to maximize JMMD such that the distributions of the source and target domains are made more distinguishable. Learning can be performed by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Experiments testify that our model yields state of the art results on standard datasets.