2D and 3D visual understanding with limited supervision

Existing fully supervised deep learning methods usually require a large number of training samples with abundant annotations for the model training, which is extremely expensive and labor-consuming. Therefore, in order to alleviate huge labeling costs, it is highly desirable to develop weakly superv...

Full description

Saved in:
Bibliographic Details
Main Author: Wu, Zhonghua
Other Authors: Lin Guosheng
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/164693
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English