https://scholars.lib.ntu.edu.tw/handle/123456789/639889
Title: | Domain-Adaptive Mean Teacher for Category-Level Object Pose Estimation | Authors: | Hsieh, I. Ju Lau, Yo Chung Kao, Peng Yuan Hung, Shih Ping YI-PING HUNG |
Keywords: | category-level object pose estimation | deep learning | domain adversarial training | Mean Teacher | unsupervised domain adaptation | Issue Date: | 6-Dec-2023 | Source: | Proceedings of the 5th ACM International Conference on Multimedia in Asia, MMAsia 2023 | Abstract: | Category-level object pose estimation aims at predicting 6-DoF object poses for previously unseen objects. Current methods mostly rely on ground-truth labels such as object poses and CAD models. However, annotating these labels manually is time-consuming and error-prone in the real-world scenario. Hence, we propose a novel method to solve unsupervised domain adaptation (UDA) for category-level object pose estimation. We adopt a teacher-student framework to utilize both labeled synthetic data and unlabeled real-world data. The student and the teacher are trained to make consistent predictions under different perturbations. Furthermore, we introduce domain adversarial training to bridge the domain gap between synthetic and real-world data. To prevent false feature alignment between domains, we adopt multiple discriminators instead of a single one and perform category-aware alignments. Extensive experiments show that our method achieves state-of-the-art performance on the REAL275 dataset. Through ablation studies, we also demonstrate that our method is not restricted to certain network architecture and can serve as a general UDA method for category-level object pose estimation. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/639889 | ISBN: | 9798400702051 | DOI: | 10.1145/3595916.3626395 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.