Improving Online Source-Free Domain Adaptation for Object Detection by Unsupervised Data Acquisition
Abstract
Effective object detection in autonomous vehicles is challenged by deployment in diverse and unfamiliar environments. Online Source-Free Domain Adaptation (O-SFDA) offers model adaptation using a stream of unlabeled data from a target domain in an online manner. However, not all captured frames contain information beneficial for adaptation, especially in the presence of redundant data and class imbalance issues. This paper introduces a novel approach to enhance O-SFDA for adaptive object detection through unsupervised data acquisition. Our methodology prioritizes the most informative unlabeled frames for inclusion in the online training process. Empirical evaluation on a real-world dataset reveals that our method outperforms existing state-of-the-art O-SFDA techniques, demonstrating the viability of unsupervised data acquisition for improving the adaptive object detector.
Cite
Text
Shi et al. "Improving Online Source-Free Domain Adaptation for Object Detection by Unsupervised Data Acquisition." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91767-7_14Markdown
[Shi et al. "Improving Online Source-Free Domain Adaptation for Object Detection by Unsupervised Data Acquisition." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/shi2024eccvw-improving/) doi:10.1007/978-3-031-91767-7_14BibTeX
@inproceedings{shi2024eccvw-improving,
title = {{Improving Online Source-Free Domain Adaptation for Object Detection by Unsupervised Data Acquisition}},
author = {Shi, Xiangyu and Qiao, Yanyuan and Wu, Qi and Liu, Lingqiao and Dayoub, Feras},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {195-205},
doi = {10.1007/978-3-031-91767-7_14},
url = {https://mlanthology.org/eccvw/2024/shi2024eccvw-improving/}
}