Nov 27, 2019 · This novel CCDA method encourages the network to shift the domain in a class-conditional manner, and it equalizes loss over classes. We evaluate ...

Mar 22, 2024 · We address this problem by introducing a Class-Conditional Domain Adaptation (CCDA) method. This incorporates a class-conditional multi-scale discriminator and ...

Together, they measure the segmentation, shift the domain in a class-conditional manner, and equalize the loss over classes. Experimental results demonstrate ...

This incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and adaptation. Together, they measure the ...

Together, they measure the segmentation, shift the domain in a class-conditional manner, and equalize the loss over classes. Experimental results demonstrate ...

A Class-Conditional Domain Adaptation (CCDA) method that incorporates a class-conditional multi-scale discriminator and class-conditional losses for both ...

This incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and adaptation. Together, they measure the ...

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which ...

Yue Wang, Yuke Li, James H. Elder, Runmin Wu, Huchuan Lu: Class-Conditional Domain Adaptation on Semantic Segmentation. CoRR abs/1911.11981 (2019).

A novel unsupervised domain adaptation method for semantic segmentation models, tailored for condition-level adaptation.