Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Unsupervised Domain Adaptation with Multi-kernel MMD
Ist Teil von
2021 40th Chinese Control Conference (CCC), 2021, p.8576-8581
Ort / Verlag
Technical Committee on Control Theory, Chinese Association of Automation
Erscheinungsjahr
2021
Quelle
IEL
Beschreibungen/Notizen
In this work, we propose a method to solve the problem of unsupervised domain adaptation. Most of existing works are based on adversarial learning method, which obtains the features of inputs through a feature extraction network, and distinguishes the features by a domain classifier that can generate domain-invariant features. The domain-invariant features is used as the input of a classifier (fully connected network) to get the final category of the image. However, in fact, each layer of the fully connected network can be regarded as the domain invariant feature. Consequently, we employ the last layer as domain-invariant features which can also be considered as a probability distribution. Finally, the domain discrepancies between the distribution in source domain and target domain is measured by multi-kernel MMD, which is what we need to minimize. Experimental evidences show that the proposed method achieves satisfactory results on standard domain adapatation benchmarks.