UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation

Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real world. To tackle this problem, we propose an unsupervised domain adaptation (UDA) for category-level object pose estimati...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-04
Main Authors: Lee, Taeyeop, Lee, Byeong-Uk, Shin, Inkyu, Choe, Jaesung, Shin, Ukcheol, In So Kweon, Kuk-Jin Yoon
Format: Article
Language:English
Subjects:
Adaptation
Domains
Labels
Learning
Supervised learning
Teachers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real world. To tackle this problem, we propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called UDA-COPE. Inspired by recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain pose labels. We also introduce a bidirectional filtering method between the predicted normalized object coordinate space (NOCS) map and observed point cloud, to not only make our teacher network more robust to the target domain but also to provide more reliable pseudo labels for the student network training. Extensive experimental results demonstrate the effectiveness of our proposed method both quantitatively and qualitatively. Notably, without leveraging target-domain GT labels, our proposed method achieved comparable or sometimes superior performance to existing methods that depend on the GT labels.
ISSN:2331-8422