Name
Abstract | ||
|---|---|---|
Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. 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. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptation scenario. 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. The domain discrepancy is further reduced using an optimal multikernel selection method for mean embedding matching. DAN can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Extensive empirical evidence shows that the proposed architecture yields state-of-the-art image classification error rates on standard domain adaptation benchmarks. |
Year | Venue | Field |
|---|---|---|
2015 | International Conference on Machine Learning | Domain adaptation,Convolutional neural network,Computer science,Multikernel,Artificial intelligence,Contextual image classification,Artificial neural network,Kernel (linear algebra),Embedding,Pattern recognition,Algorithm,Reproducing kernel Hilbert space,Machine learning |
DocType | Volume | Citations |
Journal | abs/1502.02791 | 286 |
PageRank | References | Authors |
7.10 | 31 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mingsheng Long | 1 | 1421 | 55.15 |
| Yue Cao | 2 | 574 | 21.49 |
| Jianmin Wang | 3 | 2446 | 156.05 |
| Michael I. Jordan | 4 | 31220 | 3640.80 |