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. In this paper, we propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE. We 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, our approach processes the test data in a sequential, online manner, and it does not require access to the source domain at runtime. Extensive experimental results demonstrate that the proposed pose ensemble and the self-training loss improve category-level object pose performance during test time under both semi-supervised and unsupervised settings. 



Qualitative comparison with the no adaptation and our test-time adaptation.



  title={{TTA-COPE}: Test-Time Adaptation for Category-Level Object Pose Estimation},

  author={Lee, Taeyeop and Tremblay, Jonathan and Blukis, Valts and Wen, Bowen and Lee, Byeong-Uk and Shin, Inkyu and Birchfield, Stan and Kweon, In So and Yoon, Kuk-Jin},

  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},




If you have any questions, please feel free to contact Taeyeop Lee.