Driving with InternVL: Oustanding Champion in the Track on Driving with Language of the Autonomous Grand Challenge at CVPR 2024
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_ | 1866912150049521664 |
|---|---|
| author | Li, Jiahan Li, Zhiqi Lu, Tong |
| author_facet | Li, Jiahan Li, Zhiqi Lu, Tong |
| contents | This technical report describes the methods we employed for the Driving with Language track of the CVPR 2024 Autonomous Grand Challenge. We utilized a powerful open-source multimodal model, InternVL-1.5, and conducted a full-parameter fine-tuning on the competition dataset, DriveLM-nuScenes. To effectively handle the multi-view images of nuScenes and seamlessly inherit InternVL's outstanding multimodal understanding capabilities, we formatted and concatenated the multi-view images in a specific manner. This ensured that the final model could meet the specific requirements of the competition task while leveraging InternVL's powerful image understanding capabilities. Meanwhile, we designed a simple automatic annotation strategy that converts the center points of objects in DriveLM-nuScenes into corresponding bounding boxes. As a result, our single model achieved a score of 0.6002 on the final leadboard. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07247 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Driving with InternVL: Oustanding Champion in the Track on Driving with Language of the Autonomous Grand Challenge at CVPR 2024 Li, Jiahan Li, Zhiqi Lu, Tong Computer Vision and Pattern Recognition This technical report describes the methods we employed for the Driving with Language track of the CVPR 2024 Autonomous Grand Challenge. We utilized a powerful open-source multimodal model, InternVL-1.5, and conducted a full-parameter fine-tuning on the competition dataset, DriveLM-nuScenes. To effectively handle the multi-view images of nuScenes and seamlessly inherit InternVL's outstanding multimodal understanding capabilities, we formatted and concatenated the multi-view images in a specific manner. This ensured that the final model could meet the specific requirements of the competition task while leveraging InternVL's powerful image understanding capabilities. Meanwhile, we designed a simple automatic annotation strategy that converts the center points of objects in DriveLM-nuScenes into corresponding bounding boxes. As a result, our single model achieved a score of 0.6002 on the final leadboard. |
| title | Driving with InternVL: Oustanding Champion in the Track on Driving with Language of the Autonomous Grand Challenge at CVPR 2024 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.07247 |