Segment scene in new domain using multiple sets of discrepancy features with Feng
Segment scene in new domain using multiple sets of discrepancy features with Feng
Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2309.16127
arXiv PDF paper https://arxiv.org/pdf/2309.16127.pdf
Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation.
... paper proposes the Object Style Compensation, where ... construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features.
The discrepancy features in a set capture the style changes of the same category's object instances adapted from target to source domains.
... learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory.
With this memory, ... select appropriate discrepancy features for compensating the style information of the object instances of various categories, adapting the object styles to a unified style of source domain.
... method ... yielding state-of-the-art results on different datasets.
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
Kommentare