Progressive Domain Adaptation for Object Detection
Abstract
Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribution. Domain adaptation provides a solution by adapting existing labels to the target testing data. However, a large gap between domains could make adaptation a challenging task, which leads to unstable training processes and sub-optimal solutions. In this paper, we pro- pose to bridge the domain gap with an intermediate domain and then progressively solve easier adaptation subtasks. Experimental results show that our method performs favorably against the state-of-the-art method in terms of the model test performance on the target domain.
Cite
Text
Hsu et al. "Progressive Domain Adaptation for Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Hsu et al. "Progressive Domain Adaptation for Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/hsu2019cvprw-progressive/)BibTeX
@inproceedings{hsu2019cvprw-progressive,
title = {{Progressive Domain Adaptation for Object Detection}},
author = {Hsu, Han-Kai and Hung, Wei-Chih and Tseng, Hung-Yu and Yao, Chun-Han and Tsai, Yi-Hsuan and Singh, Maneesh and Yang, Ming-Hsuan},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {1-5},
url = {https://mlanthology.org/cvprw/2019/hsu2019cvprw-progressive/}
}