FCNs in the Wild
时间: 2024-04-23 14:28:50 浏览: 13
FCNs in the Wild是一种用于像素级对抗和基于约束的适应的方法,用于实现不同数据集的语义分割。该方法的动机是当训练数据和测试数据不同域时,以前的方法效果较差。它提出了无监督对抗方式来解决像素预测问题,并结合全局和类别特定的适应技术。该方法假设源域和目标域共享相同的标签空间,并且源模型在目标域上的性能优于随机猜测。创新之处在于提出了无监督域适应方法,可以迁移FCN结果的图像域,并结合全局和局部对齐方法来提高性能。\[1\]
#### 引用[.reference_title]
- *1* [2016-CVPR-FCN in the Wild 论文学习笔记](https://blog.csdn.net/weixin_43795588/article/details/126771737)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insert_down1,239^v3^insert_chatgpt"}} ] [.reference_item]
- *2* [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://blog.csdn.net/odssodssey/article/details/123266187)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insert_down1,239^v3^insert_chatgpt"}} ] [.reference_item]
- *3* [16-FCNs in the Wild- Pixel-level Adversarial and Constraint-based Adaptation](https://blog.csdn.net/u010067397/article/details/84990515)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insert_down1,239^v3^insert_chatgpt"}} ] [.reference_item]
[ .reference_list ]