Name
Abstract | ||
|---|---|---|
Deep learning techniques are renowned for supporting effective transfer learning. However, as we demonstrate, the transferred representations support only a few modes of separation and much of its dimensionality is unutilized. In this work, we suggest to learn, in the source domain, multiple orthogonal classifiers. We prove that this leads to a reduced rank representation, which, however, supports more discriminative directions. Interestingly, the softmax probabilities produced by the multiple classifiers are likely to be identical. Experimental results, on CIFAR-100 and LFW, further demonstrate the effectiveness of our method. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/CVPR.2016.429 | 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
Field | DocType | Volume |
Pattern recognition,Softmax function,Computer science,Transfer of learning,Curse of dimensionality,Artificial intelligence,Deep learning,Multiverse,Discriminative model,Machine learning | Conference | abs/1511.09033 |
Issue | ISSN | Citations |
1 | 1063-6919 | 5 |
PageRank | References | Authors |
0.49 | 25 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Littwin, E. | 1 | 6 | 2.53 |
| Lior Wolf | 2 | 5501 | 352.38 |