Domain Transfer Multiple Kernel Learning

Authors:
Lixin Duan;Ivor W. Tsang;Dong Xu
Affiliations:
Nanyang Technological University, Singapore;Nanyang Technological University, Singapore;Nanyang Technological University, Singapore
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2012

Citing 0
Cited 6

On minimum distribution discrepancy support vector machine for domain adaptation

Pattern Recognition
Road scene segmentation from a single image

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
FIDOS: A generalized Fisher based feature extraction method for domain shift

Pattern Recognition
Multiple feature kernel hashing for large-scale visual search

Pattern Recognition
Beyond cross-domain learning: Multiple-domain nonnegative matrix factorization

Engineering Applications of Artificial Intelligence
Locality and similarity preserving embedding for feature selection

Neurocomputing

Quantified Score

Hi-index	0.14

Visualization

Abstract

Cross-domain learning methods have shown promising results by leveraging labeled patterns from the auxiliary domain to learn a robust classifier for the target domain which has only a limited number of labeled samples. To cope with the considerable change between feature distributions of different domains, we propose a new cross-domain kernel learning framework into which many existing kernel methods can be readily incorporated. Our framework, referred to as Domain Transfer Multiple Kernel Learning (DTMKL), simultaneously learns a kernel function and a robust classifier by minimizing both the structural risk functional and the distribution mismatch between the labeled and unlabeled samples from the auxiliary and target domains. Under the DTMKL framework, we also propose two novel methods by using SVM and prelearned classifiers, respectively. Comprehensive experiments on three domain adaptation data sets (i.e., TRECVID, 20 Newsgroups, and email spam data sets) demonstrate that DTMKL-based methods outperform existing cross-domain learning and multiple kernel learning methods.