Segment objects in new domain by unsupervised training with boxes in old domain with WUDA
Segment objects in new domain by unsupervised training with boxes in old domain with WUDA
WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels
arXiv paper abstract https://arxiv.org/abs/2210.02088v1
arXiv PDF paper https://arxiv.org/pdf/2210.02088v1.pdf
Unsupervised domain adaptation (UDA) for semantic segmentation addresses the cross-domain problem with fine source domain labels.
However, the acquisition of semantic labels has always been a difficult step, many scenarios only have weak labels (e.g. bounding boxes).
... paper defines a new task: unsupervised domain adaptation based on weak source domain labels (WUDA) ... proposes ... 1) Perform weakly supervised semantic segmentation in the source domain, and then implement unsupervised domain adaptation;
2) Train an object detection model using source domain data, then detect objects in the target domain and implement weakly supervised semantic segmentation.
... construct dataset pairs with a wide range of domain shifts and conduct extended experiments to analyze the impact of different domain shifts on the two frameworks.
... apply the metric representation shift to urban landscape image segmentation for the first time ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
コメント