Object-Aware Domain Generalization for Object Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 2947-2955
DOI: 10.1609/aaai.v38i4.28076 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Wooju Lee und 3 weiteren Autor:innen. Die Arbeit wurde bisher 57-mal zitiert (Crossref).
Abstract (Originalsprache)
Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. OA-Mix generates multi-domain data with multi-level transformation and object-aware mixing strategy. OA-Loss enables models to learn domain-invariant representations for objects and backgrounds from the original and OA-Mixed images. Our proposed method outperforms state-of-the-art works on standard benchmarks. Our code is available at https://github.com/WoojuLee24/OA-DG.
Zitieren
APA
Lee, W., Hong, D., Lim, H., & Myung, H. (2024). Object-Aware Domain Generalization for Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 2947-2955. https://doi.org/10.1609/aaai.v38i4.28076
Vancouver
Lee W, Hong D, Lim H, Myung H. Object-Aware Domain Generalization for Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):2947-2955. doi:10.1609/aaai.v38i4.28076
BibTeX
@article{Lee2024,
author = {Lee, Wooju and Hong, Dasol and Lim, Hyungtae and Myung, Hyun},
title = {Object-Aware Domain Generalization for Object Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {4},
pages = {2947--2955},
doi = {10.1609/aaai.v38i4.28076}
}
EUVIMED