Explain image classifier by showing features in source and target domains with XSDA-Net
Explain image classifier by showing features in source and target domains with XSDA-Net
Explainable Supervised Domain Adaptation
arXiv paper abstract https://arxiv.org/abs/2205.09943
arXiv PDF paper https://arxiv.org/pdf/2205.09943v1.pdf
Domain adaptation techniques have contributed to the success of deep learning.
Leveraging knowledge from an auxiliary source domain for learning in labeled data-scarce target domain is fundamental to domain adaptation.
… While … techniques result in increasing accuracy … knowledge leveraged from the source domain, remains unclear.
… proposes an explainable by design supervised domain adaptation framework — XSDA-Net.
… mechanism into the XSDA-Net to explain the prediction of a test instance in terms of similar-looking regions in the source and target train images.
… demonstrate the utility of … framework by curating the domain adaptation settings on datasets … known to exhibit part-based explainability.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
