Get object pose in new domain without labels by automatically fine-tune on new images with TTA-COPE
Get object pose in new domain without labels by automatically fine-tune on new images with TTA-COPE
TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
arXiv paper abstract https://arxiv.org/abs/2303.16730
arXiv PDF paper https://arxiv.org/pdf/2303.16730.pdf
Project page https://sites.google.com/view/taeyeop-lee/ttacope
Test-time adaptation methods have been gaining attention recently as a practical solution for addressing source-to-target domain gaps by gradually updating the model without requiring labels on the target data.
... propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE.
... design a pose ensemble approach with a self-training loss using pose-aware confidence.
Unlike previous unsupervised domain adaptation methods for category-level object pose estimation ... approach processes the test data in a sequential, online manner, and it does not require access to the source domain at runtime.
... demonstrate ... improve category-level object pose performance during test time under both semi-supervised and unsupervised settings.
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