Deep CORAL: Correlation Alignment for Deep Domain Adaptation
Preprint
Abstract
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate for the degradation in performance due to domain shift. In this paper, we address the case when the target domain is unlabeled, requiring unsupervised adaptation. CORAL is a "frustratingly easy" unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation. Here, we extend CORAL to learn a nonlinear transformation that aligns correlations of layer activations in deep neural networks (Deep CORAL). Experiments on standard benchmark datasets show state-of-the-art performance.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Return of Frustratingly Easy Domain AdaptationProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Learning Deep Object Detectors from 3D Models2015
- Subspace Distribution Alignment for Unsupervised Domain Adaptation2015
- From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains2014
- Unsupervised Visual Domain Adaptation Using Subspace Alignment2013
- Geodesic flow kernel for unsupervised domain adaptation2012
- Domain adaptation for object recognition: An unsupervised approach2011
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- Correcting Sample Selection Bias by Unlabeled Data2007