Bharat Sukhwani, Hong Min, et al.
IEEE Micro
Transfer learning uses trained weights from a source model as the initial weights for the training of a target dataset. A well chosen source with a large number of labeled data leads to significant improvement in accuracy. We demonstrate a technique that automatically labels large unlabeled datasets so that they can train source models for transfer learning. We experimentally evaluate this method, using a baseline dataset of human-annotated ImageNet1K labels, against five variations of this technique. We show that the performance of these automatically trained models come within 6% of baseline.
Bharat Sukhwani, Hong Min, et al.
IEEE Micro
Anshul Gandhi, Parijat Dube, et al.
Software and Systems Modeling
Lipyeow Lim, Bishwaranjan Bhattacharjee
HICSS 2011
Parijat Dube, Zhen Liu, et al.
GLOBECOM 2005