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 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.
Code (0)
등록된 구현이 없습니다.
Tasks
6D Pose Estimation using RGBDDomain AdaptationObjectPose EstimationSelf-Supervised LearningUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
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 p…
Domain AdaptationObjectPose EstimationTest-time Adaptation+1Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
Unsupervised domain adaptation aims to generalize the supervised model trained on a source domain to an unlabeled target domain. Marginal distribution alignment of feature spaces is widely used to reduce the domain discr…
ClassificationDomain AdaptationGeneral Classificationimage-classification+2Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks. However, these methods focus only on global distribution adaptation and ignor…
Domain AdaptationImage SegmentationSemantic SegmentationUnsupervised Domain AdaptationPrototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domai…
Contrastive LearningDomain AdaptationSelf-Supervised LearningSemantic Segmentation+1Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propos…
Contrastive LearningDomain AdaptationRepresentation LearningUnsupervised Domain Adaptation