A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track
Guardado en:
| Publicado en: | arXiv.org (Feb 27, 2024), p. n/a |
|---|---|
| Autor principal: | |
| Otros Autores: | , , , , |
| Publicado: |
Cornell University Library, arXiv.org
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full text outside of ProQuest |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2932621464 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2932621464 | ||
| 045 | 0 | |b d20240227 | |
| 100 | 1 | |a Chen, Zehui | |
| 245 | 1 | |a A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track | |
| 260 | |b Cornell University Library, arXiv.org |c Feb 27, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a In this report, we present our solution to the multi-task robustness track of the 1st Visual Continual Learning (VCL) Challenge at ICCV 2023 Workshop. We propose a vanilla framework named UniNet that seamlessly combines various visual perception algorithms into a multi-task model. Specifically, we choose DETR3D, Mask2Former, and BinsFormer for 3D object detection, instance segmentation, and depth estimation tasks, respectively. The final submission is a single model with InternImage-L backbone, and achieves a 49.6 overall score (29.5 Det mAP, 80.3 mTPS, 46.4 Seg mAP, and 7.93 silog) on SHIFT validation set. Besides, we provide some interesting observations in our experiments which may facilitate the development of multi-task learning in dense visual prediction. | |
| 653 | |a Visual tasks | ||
| 653 | |a Instance segmentation | ||
| 653 | |a Robustness (mathematics) | ||
| 653 | |a Visual perception | ||
| 653 | |a Learning | ||
| 653 | |a Object recognition | ||
| 653 | |a Visual perception driven algorithms | ||
| 700 | 1 | |a Wang, Qiuchen | |
| 700 | 1 | |a Li, Zhenyu | |
| 700 | 1 | |a Liu, Jiaming | |
| 700 | 1 | |a Zhang, Shanghang | |
| 700 | 1 | |a Zhao, Feng | |
| 773 | 0 | |t arXiv.org |g (Feb 27, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2932621464/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2402.17319 |