Name
Abstract | ||
|---|---|---|
Transfer learning aims to address the problem where we lack the labeled data for training in one domain while utilizing the sufficient training data from other relevant domains. The problem becomes even more challenging when there are no labeled data in the target domain to build the association between two domains, which is more common in real-world scenarios. In this paper, we tackle with the challenge through learning the shared subspace across domains. The subspace is able to capture the intrinsic domain invariant innate characteristics for feature representations. Meanwhile in the learning procedure we train the classifiers in the source domain and predict the labels in the target domain simultaneously. We also incorporate the inherent data structure in the predicted labels to enhance the robustness against the misclassification. Extensive experimental evaluations on the public datasets demonstrate the effectiveness and promise of our method compared with the state-of-the-art transfer learning methods. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICPR.2014.673 | ICPR |
Keywords | Field | DocType |
feature representations,unsupervised transfer classification,inherent data structure,pattern classification,data structures,cross domain shared subspace learning,public datasets,unsupervised learning | Data structure,Multi-task learning,Semi-supervised learning,Subspace topology,Pattern recognition,Computer science,Transfer of learning,Robustness (computer science),Unsupervised learning,Invariant (mathematics),Artificial intelligence,Machine learning | Conference |
ISSN | Citations | PageRank |
1051-4651 | 0 | 0.34 |
References | Authors | |
9 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zheng Fang | 1 | 6 | 0.75 |
| Zhongfei (Mark) Zhang | 2 | 2451 | 164.30 |