Automatic Labeling of Data for Transfer Learning
Parijat Dube, Bishwaranjan Bhattacharjee, Siyu Huo, Patrick Watson, Brian Belgodere; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 122-129
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.
Related Material
[pdf]
[
bibtex]
@InProceedings{Dube_2019_CVPR_Workshops,
author = {Dube, Parijat and Bhattacharjee, Bishwaranjan and Huo, Siyu and Watson, Patrick and Belgodere, Brian},
title = {Automatic Labeling of Data for Transfer Learning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}