Segment scene in new domain with semi-supervised learning by intra-domain target information with Fu
Segment scene in new domain with semi-supervised learning by intra-domain target information with Fu
Semi-supervised Domain Adaptation with Inter and Intra-domain Mixing for Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2308.15855
arXiv PDF paper https://arxiv.org/pdf/2308.15855.pdf
Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real application.
... semi-supervised domain adaptation (SSDA) has been proposed ... focus on leveraging the unlabeled target data and source data.
... highlight the significance of exploiting the intra-domain information between the limited labeled target data and unlabeled target data, as it greatly benefits domain adaptation.
Instead of solely using the scarce labeled data for supervision, ... propose a novel SSDA framework that incorporates both inter-domain mixing and intra-domain mixing, where inter-domain mixing mitigates the source-target domain gap and intra-domain mixing enriches the available target domain information.
By simultaneously learning from inter-domain mixing and intra-domain mixing, the network can capture more domain-invariant features and promote its performance on the target domain.
... demonstrate the effectiveness of ... method, surpassing previous methods by a large margin.
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
Comments