TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Abstract

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.

Cite

Text

Lee et al. "TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.02039

Markdown

[Lee et al. "TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/lee2023cvpr-ttacope/) doi:10.1109/CVPR52729.2023.02039

BibTeX

@inproceedings{lee2023cvpr-ttacope,
  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 = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {21285-21295},
  doi       = {10.1109/CVPR52729.2023.02039},
  url       = {https://mlanthology.org/cvpr/2023/lee2023cvpr-ttacope/}
}