Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929478908772352 |
|---|---|
| author | Shi, Xiangyu Qiao, Yanyuan Wu, Qi Liu, Lingqiao Dayoub, Feras |
| author_facet | Shi, Xiangyu Qiao, Yanyuan Wu, Qi Liu, Lingqiao Dayoub, Feras |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_19258 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition Shi, Xiangyu Qiao, Yanyuan Wu, Qi Liu, Lingqiao Dayoub, Feras Computer Vision and Pattern Recognition 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. |
| title | Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.19258 |