7/5/2023 0 Comments Deep adaptation paperThe domain discrepancy is further reduced using an optimal multi-kernel selection method for mean embedding matching. In DAN, hidden representations of all task-specific layers are embedded in a reproducing kernel Hilbert space where the mean embeddings of different domain distributions can be explicitly matched. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptation scenario. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation.
0 Comments
Leave a Reply. |