Discovering latent domains for multisource domain adaptation

Authors:
Judy Hoffman;Brian Kulis;Trevor Darrell;Kate Saenko
Affiliations:
EECS, UC Berkeley, Berkeley, California, USA,ICSI, Berkeley, California;Ohio State University, Columbus, Ohio;EECS, UC Berkeley, Berkeley, California, USA,ICSI, Berkeley, California;EECS, UC Berkeley, Berkeley, California, USA,ICSI, Berkeley, California, USA,Harvard University, Cambridge, Massachusetts
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Year:
2012

Citing 13
Cited 0

Constrained K-means Clustering with Background Knowledge

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
A probabilistic framework for semi-supervised clustering

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Semi-supervised graph clustering: a kernel approach

ICML '05 Proceedings of the 22nd international conference on Machine learning
Cross-domain video concept detection using adaptive svms

Proceedings of the 15th international conference on Multimedia
Constrained Clustering: Advances in Algorithms, Theory, and Applications

Constrained Clustering: Advances in Algorithms, Theory, and Applications
Dataset Shift in Machine Learning

Dataset Shift in Machine Learning
Learning to Recognize Activities from the Wrong View Point

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Domain adaptation from multiple sources via auxiliary classifiers

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Adapting visual category models to new domains

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Unbiased look at dataset bias

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
What you saw is not what you get: Domain adaptation using asymmetric kernel transforms

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Source constrained clustering

ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Domain adaptation for object recognition: An unsupervised approach

ICCV '11 Proceedings of the 2011 International Conference on Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent domain adaptation methods successfully learn cross-domain transforms to map points between source and target domains. Yet, these methods are either restricted to a single training domain, or assume that the separation into source domains is known a priori. However, most available training data contains multiple unknown domains. In this paper, we present both a novel domain transform mixture model which outperforms a single transform model when multiple domains are present, and a novel constrained clustering method that successfully discovers latent domains. Our discovery method is based on a novel hierarchical clustering technique that uses available object category information to constrain the set of feasible domain separations. To illustrate the effectiveness of our approach we present experiments on two commonly available image datasets with and without known domain labels: in both cases our method outperforms baseline techniques which use no domain adaptation or domain adaptation methods that presume a single underlying domain shift.