On the Importance of Dual-Space Augmentation for Domain Generalized Object Detection
Abstract
The distribution gap between training data and real-world data often causes significant performance drops in networks trained via naive supervised learning. To address this domain generalization methods have been developed to gain robust performance in unseen domains. In this paper we propose a single-domain generalized object detection (S-DGOD) method. Unlike previous works we utilize both image-level and feature-level augmentations and experimentally demonstrate their synergistic effects. Image-level augmentations expand the source domain while feature-level augmentations leverage CLIP to incorporate potential domain descriptions. Our method achieves superior performance with 29.2% mAP on the Cityscapes-C and 37.1% mAP on the Diverse-Weather dataset.
Cite
Text
Park et al. "On the Importance of Dual-Space Augmentation for Domain Generalized Object Detection." Winter Conference on Applications of Computer Vision, 2025.Markdown
[Park et al. "On the Importance of Dual-Space Augmentation for Domain Generalized Object Detection." Winter Conference on Applications of Computer Vision, 2025.](https://mlanthology.org/wacv/2025/park2025wacv-importance/)BibTeX
@inproceedings{park2025wacv-importance,
title = {{On the Importance of Dual-Space Augmentation for Domain Generalized Object Detection}},
author = {Park, Hayoung and Cho, Choongsang and Kim, Guisik},
booktitle = {Winter Conference on Applications of Computer Vision},
year = {2025},
pages = {9408-9418},
url = {https://mlanthology.org/wacv/2025/park2025wacv-importance/}
}