Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
Abstract
Recently proposed domain adaptation methods retrain the network parameters and overcome the domain shift issue to a large extent. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes. To this end, we first analyze the output of each convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer convolutional filters that are badly affected by the domain shift are reconstructed based on less affected ones.
Cite
Text
Aljundi and Tuytelaars. "Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-49409-8_43Markdown
[Aljundi and Tuytelaars. "Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/aljundi2016eccv-lightweight/) doi:10.1007/978-3-319-49409-8_43BibTeX
@inproceedings{aljundi2016eccv-lightweight,
title = {{Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction}},
author = {Aljundi, Rahaf and Tuytelaars, Tinne},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {508-515},
doi = {10.1007/978-3-319-49409-8_43},
url = {https://mlanthology.org/eccv/2016/aljundi2016eccv-lightweight/}
}