Efficient Learning of Domain-Invariant Image Representations
Title | Efficient Learning of Domain-Invariant Image Representations |
Publication Type | Conference Paper |
Year of Publication | 2013 |
Authors | Hoffman, J., Rodner E., Donahue J., Darrell T., & Saenko K. |
Other Numbers | 3439 |
Abstract | We present an algorithm that learns representations which explicitly compensate for domain mismatch and which can be efficiently realized as linear classifiers. Specifically, we form a linear transformation that maps features from the target (test) domain to the source (training) domain as part of training the classifier. We optimize both the transformation and classifier parameters jointly, and introduce an efficient cost function based on misclassification loss.Our method combines several features previously unavailable in a single algorithm: multi-class adaptation through representation learning, ability to map across heterogeneous feature spaces, and scalability to large datasets. We present experiments on several image datasets that demonstrate improved accuracy and computational advantages compared to previous approaches. |
Acknowledgment | This work was partially funded by the Deutscher Akademischer Austausch Dienst (DAAD) through a postdoctoral fellowship. |
URL | https://www.icsi.berkeley.edu/pubs/vision/efficientlearning13.pdf |
Bibliographic Notes | Proceedings of International Conference on Learning Representations (ICLR 2013), Scottsdale, Arizona |
Abbreviated Authors | J. Hoffman, E. Rodner, J. Donahue, T. Darrell, and K. Saenko |
ICSI Research Group | Vision |
ICSI Publication Type | Article in conference proceedings |