Learning Transferable Features with Deep Adaptation Networks
read the original 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 multi-kernel 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Learning to learn with quantum neural networks via classical neural networks
Classical RNNs trained on small instances provide parameter initializations for QAOA and VQE that reduce total optimization iterations and generalize across problem sizes.
-
How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework
The authors introduce a register-aware evaluation framework that compares LLM outputs to human reference corpora via Biber's lexico-grammatical features and MMD across five English registers.
-
Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy
Unsupervised domain adaptation via feature alignment raises radioisotope identification accuracy on real LaBr3 gamma spectra from 0.754 to 0.904 for models trained only on synthetic data.
-
Environment Probing Interaction Policies
EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.
-
Unsupervised Domain Adaptation via Calibrating Uncertainties
A new regularization approach for unsupervised domain adaptation that calibrates Renyi entropy of uncertainties estimated via variational Bayes.
-
Remaining Useful Lifetime Prediction via Deep Domain Adaptation
A domain-adversarial LSTM learns invariant features from labeled source RUL data to enable predictions in unlabeled target domains with distribution shifts due to varying conditions and fault modes.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.