Progressive Domain Adaptation for Object Detection

Han-Kai Hsu, Wei-Chih Hung, Hung-Yu Tseng, Chun-Han Yao, Yi-Hsuan Tsai, Maneesh Singh, Ming-Hsuan Yang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 1-5

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.

Related Material


[pdf] [dataset]
[bibtex]
@InProceedings{Hsu_2019_CVPR_Workshops,
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},
title = {Progressive Domain Adaptation for Object Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}