Co-regularized Alignment for Unsupervised Domain Adaptation
Preprint
Abstract
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}. It can be expensive or even infeasible to obtain required amount of labeled data in all possible domains. Unsupervised domain adaptation sets out to address this problem, aiming to learn a good predictive model for the target domain using labeled examples from the source domain but only unlabeled examples from the target domain. Domain alignment approaches this problem by matching the source and target feature distributions, and has been used as a key component in many state-of-the-art domain adaptation methods. However, matching the marginal feature distributions does not guarantee that the corresponding class conditional distributions will be aligned across the two domains. We propose co-regularized domain alignment for unsupervised domain adaptation, which constructs multiple diverse feature spaces and aligns source and target distributions in each of them individually, while encouraging that alignments agree with each other with regard to the class predictions on the unlabeled target examples. The proposed method is generic and can be used to improve any domain adaptation method which uses domain alignment. We instantiate it in the context of a recent state-of-the-art method and observe that it provides significant performance improvements on several domain adaptation benchmarks.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping2018
- Virtual and Real World Adaptation for Pedestrian DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains2014
- Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk MinimizationIEEE Transactions on Information Theory, 2010
- A theory of learning from different domainsMachine Learning, 2009
- Tri-training: exploiting unlabeled data using three classifiersIEEE Transactions on Knowledge and Data Engineering, 2005
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000
- Ensemble learning via negative correlationNeural Networks, 1999