PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (20) · 21815-21823
DOI: 10.1609/aaai.v39i20.35487 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xiaoran Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref).
Abstract (Originalsprache)
Single-Domain Generalized Object Detection (S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on data augmentation strategies, including a composition of visual transformations, to enhance the detector's generalization ability. However, the absence of real-world prior knowledge hinders data augmentation from contributing to the diversity of training data distributions. To address this issue, we propose PhysAug, a novel physical model-based non-ideal imaging condition data augmentation method, to enhance the adaptability of the S-DGOD tasks. Drawing upon the principles of atmospheric optics, we develop a universal perturbation model that serves as the foundation for our proposed PhysAug. Given that visual perturbations typically arise from the interaction of light with atmospheric particles, the image frequency spectrum is harnessed to simulate real-world variations during training. This approach fosters the detector to learn domain-invariant representations, thereby enhancing its ability to generalize across various settings. Without altering the network architecture or loss function, our approach significantly outperforms the state-of-the-art across various S-DGOD datasets. In particular, it achieves a substantial improvement of 7.3% and 7.2% over the baseline on DWD and Cityscape-C, highlighting its enhanced generalizability in real-world settings.
Zitieren
APA
Xu, X., Yang, J., Shi, W., Ding, S., Luo, L., & Liu, J. (2025). PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(20), 21815-21823. https://doi.org/10.1609/aaai.v39i20.35487
Vancouver
Xu X, Yang J, Shi W, Ding S, Luo L, Liu J. PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(20):21815-21823. doi:10.1609/aaai.v39i20.35487
BibTeX
@article{Xu2025,
author = {Xu, Xiaoran and Yang, Jiangang and Shi, Wenhui and Ding, Siyuan and Luo, Luqing and Liu, Jian},
title = {PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {20},
pages = {21815--21823},
doi = {10.1609/aaai.v39i20.35487}
}
EUVIMED