Multitask Adaptation for Unlabeled Domain Using Multiple Single-Task Domains
Semantic segmentation and depth estimation tasks are crucial for autonomous driving systems, but obtaining their labels from real-world datasets is costly. To address the problem, we developed a multitask domain adaptation that uses various labeled datasets with distinct tasks to adapt the multitask...
Збережено в:
| Автори: | , , , |
|---|---|
| Формат: | Artigo |
| Мова: | Inglês |
| Опубліковано: |
IEEE
2024-01-01
|
| Серія: | IEEE Access |
| Предмети: | |
| Онлайн доступ: | https://ieeexplore.ieee.org/document/10804160/ |
| Теги: |
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|