Web: http://arxiv.org/abs/2206.03657

June 16, 2022, 1:13 a.m. | Zhuoling Li, Chuanrui Zhang, En Yu, Haoqian Wang

cs.CV updates on arXiv.org arxiv.org

The labels of monocular 3D object detection (M3OD) are expensive to obtain.
Meanwhile, there usually exists numerous unlabeled data in practical
applications, and pre-training is an efficient way of exploiting the knowledge
in unlabeled data. However, the pre-training paradigm for M3OD is hardly
studied. We aim to bridge this gap in this work. To this end, we first draw two
observations: (1) The guideline of devising pre-training tasks is imitating the
representation of the target task. (2) Combining depth estimation …

3d arxiv cv detection pre-training training

More from arxiv.org / cs.CV updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY