Back to Search
Start Over
YOLO-G: Improved YOLO for cross-domain object detection.
- Source :
- PLoS ONE; 9/11/2023, Vol. 18 Issue 9, p1-16, 16p
- Publication Year :
- 2023
-
Abstract
- Cross-domain object detection is a key problem in the research of intelligent detection models. Different from lots of improved algorithms based on two-stage detection models, we try another way. A simple and efficient one-stage model is introduced in this paper, comprehensively considering the inference efficiency and detection precision, and expanding the scope of undertaking cross-domain object detection problems. We name this gradient reverse layer-based model YOLO-G, which greatly improves the object detection precision in cross-domain scenarios. Specifically, we add a feature alignment branch following the backbone, where the gradient reverse layer and a classifier are attached. With only a small increase in computational, the performance is higher enhanced. Experiments such as Cityscapes→Foggy Cityscapes, SIM10k→Cityscape, PASCAL VOC→Clipart, and so on, indicate that compared with most state-of-the-art (SOTA) algorithms, the proposed model achieves much better mean Average Precision (mAP). Furthermore, ablation experiments were also performed on 4 components to confirm the reliability of the model. The project is available at https://github.com/airy975924806/yolo-G. [ABSTRACT FROM AUTHOR]
- Subjects :
- ALGORITHMS
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 18
- Issue :
- 9
- Database :
- Complementary Index
- Journal :
- PLoS ONE
- Publication Type :
- Academic Journal
- Accession number :
- 171877617
- Full Text :
- https://doi.org/10.1371/journal.pone.0291241