Кросс-домендік білім дистилляциясы
method
ID: crossdomainknowledgedistillation
Related Papers
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation
AbstractUnsupervised Domain Adaptation (UDA) aims to transfer the knowledge of source domain to the unlabeled target domain. Existing methods typically require to learn to adapt the target model by exploiting …...