Detect objects in new domain without labels in target by using domain-invariant frequencies with FIT
Detect objects in new domain without labels in target by using domain-invariant frequencies with FIT
FIT: Frequency-based Image Translation for Domain Adaptive Object Detection
arXiv paper abstract https://arxiv.org/abs/2303.03698
arXiv PDF paper https://arxiv.org/pdf/2303.03698.pdf
Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain.
… propose a novel Frequency-based Image Translation (FIT) framework for DAOD.
First, by keeping domain-invariant frequency components and swapping domain-specific ones, … conduct image translation to reduce domain shift at the input level.
Second, hierarchical adversarial feature learning is utilized to further mitigate the domain gap at the feature level.
Finally, … design a joint loss to train the entire network in an end-to-end manner without extra training to obtain translated images.
… demonstrate the effectiveness of … method.
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
