TY - GEN
T1 - An empirical bayes approach to contextual region classification
AU - Lazebnik, Svetlana
AU - Raginsky, Maxim
PY - 2009
Y1 - 2009
N2 - This paper presents a nonparametric approach to labeling of local image regions that is inspired by recent developments in information-theoretic denoising. The chief novelty of this approach rests in its ability to derive an unsupervised contextual prior over image classes from unlabeled test data. Labeled training data is needed only to learn a local appearance model for image patches (although additional supervisory information can optionally be incorporated when it is available). Instead of assuming a parametric prior such as a Markov random field for the class labels, the proposed approach uses the empirical Bayes technique of statistical inversion to recover a contextual model directly from the test data, either as a spatially varying or as a globally constant prior distribution over the classes in the image. Results on two challenging datasets convincingly demonstrate that useful contextual information can indeed be learned from unlabeled data.
AB - This paper presents a nonparametric approach to labeling of local image regions that is inspired by recent developments in information-theoretic denoising. The chief novelty of this approach rests in its ability to derive an unsupervised contextual prior over image classes from unlabeled test data. Labeled training data is needed only to learn a local appearance model for image patches (although additional supervisory information can optionally be incorporated when it is available). Instead of assuming a parametric prior such as a Markov random field for the class labels, the proposed approach uses the empirical Bayes technique of statistical inversion to recover a contextual model directly from the test data, either as a spatially varying or as a globally constant prior distribution over the classes in the image. Results on two challenging datasets convincingly demonstrate that useful contextual information can indeed be learned from unlabeled data.
UR - http://www.scopus.com/inward/record.url?scp=70450186103&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70450186103&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2009.5206690
DO - 10.1109/CVPRW.2009.5206690
M3 - Conference contribution
AN - SCOPUS:70450186103
SN - 9781424439935
T3 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
SP - 2380
EP - 2387
BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PB - IEEE Computer Society
T2 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Y2 - 20 June 2009 through 25 June 2009
ER -