Automatic Labeling of Data for Transfer Learning
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{dube2019automatic,
author = {Parijat Dube and Bishwaranjan Bhattacharjee and Siyu Huo and Patrick Watson and Brian M. Belgodere},
title = {{Automatic Labeling of Data for Transfer Learning}},
booktitle = {Workshops @ CVPR},
year = {2019},
url = {https://openreview.net/forum?id=CYRv6aZvHc},
}Loading related content...