SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915079346192384 |
|---|---|
| author | Huang, Binyuan Wen, Yuqing Zhao, Yucheng Hu, Yaosi Liu, Yingfei Jia, Fan Mao, Weixin Wang, Tiancai Zhang, Chi Chen, Chang Wen Chen, Zhenzhong Zhang, Xiangyu |
| author_facet | Huang, Binyuan Wen, Yuqing Zhao, Yucheng Hu, Yaosi Liu, Yingfei Jia, Fan Mao, Weixin Wang, Tiancai Zhang, Chi Chen, Chang Wen Chen, Zhenzhong Zhang, Xiangyu |
| contents | Autonomous driving progress relies on large-scale annotated datasets. In this work, we explore the potential of generative models to produce vast quantities of freely-labeled data for autonomous driving applications and present SubjectDrive, the first model proven to scale generative data production in a way that could continuously improve autonomous driving applications. We investigate the impact of scaling up the quantity of generative data on the performance of downstream perception models and find that enhancing data diversity plays a crucial role in effectively scaling generative data production. Therefore, we have developed a novel model equipped with a subject control mechanism, which allows the generative model to leverage diverse external data sources for producing varied and useful data. Extensive evaluations confirm SubjectDrive's efficacy in generating scalable autonomous driving training data, marking a significant step toward revolutionizing data production methods in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19438 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control Huang, Binyuan Wen, Yuqing Zhao, Yucheng Hu, Yaosi Liu, Yingfei Jia, Fan Mao, Weixin Wang, Tiancai Zhang, Chi Chen, Chang Wen Chen, Zhenzhong Zhang, Xiangyu Computer Vision and Pattern Recognition Robotics Autonomous driving progress relies on large-scale annotated datasets. In this work, we explore the potential of generative models to produce vast quantities of freely-labeled data for autonomous driving applications and present SubjectDrive, the first model proven to scale generative data production in a way that could continuously improve autonomous driving applications. We investigate the impact of scaling up the quantity of generative data on the performance of downstream perception models and find that enhancing data diversity plays a crucial role in effectively scaling generative data production. Therefore, we have developed a novel model equipped with a subject control mechanism, which allows the generative model to leverage diverse external data sources for producing varied and useful data. Extensive evaluations confirm SubjectDrive's efficacy in generating scalable autonomous driving training data, marking a significant step toward revolutionizing data production methods in this field. |
| title | SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2403.19438 |