Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation
Authors:
- Jie NiJNJie Ni
- Qiang QiuQQQiang Qiu
- Rama ChellappaRCRama Chellappa
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 692-699
Abstract
Domain adaptation addresses the problem where data instances of a source domain have different distributions from that of a target domain, which occurs frequently in many real life scenarios. This work focuses on unsupervised domain adaptation, where labeled data are only available in the source domain. We propose to interpolate subspaces through dictionary learning to link the source and target domains. These subspaces are able to capture the intrinsic domain shift and form a shared feature representation for cross domain recognition. Further, we introduce a quantitative measure to characterize the shift between two domains, which enables us to select the optimal domain to adapt to the given multiple source domains. We present experiments on face recognition across pose, illumination and blur variations, cross dataset object recognition, and report improved performance over the state of the art.Keywords
This publication has 19 references indexed in Scilit:
- Domain adaptation for object recognition: An unsupervised approach2011
- Task-Driven Dictionary LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- What you saw is not what you get: Domain adaptation using asymmetric kernel transforms2011
- Cross-view action recognition via view knowledge transfer2011
- Online dictionary learning for sparse coding2009
- Understanding and evaluating blind deconvolution algorithms2009
- Cross-domain video concept detection using adaptive svms2007
- Image Denoising Via Sparse and Redundant Representations Over Learned DictionariesIEEE Transactions on Image Processing, 2006
- Appearance-based face recognition and light-fieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Method of optimal directions for frame design1999