Learning visual representations without human supervision
Supervised learning with deep neural networks has achieved great success in many visual recognition tasks including classification, detection, and segmentation. However, the need for expensive human annotations makes it increasingly prohibitive to embrace the massive amount of data available in the...
Saved in:
Main Author: | Xie, Jiahao |
---|---|
Other Authors: | Chen Change Loy |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/171772 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
2D and 3D visual understanding with limited supervision
by: Wu, Zhonghua
Published: (2023) -
Semi-supervised learning for visual relation annotation
by: Tajrobehkar, Mitra
Published: (2022) -
Learning to control visual data translation
by: Koksal, Ali
Published: (2023) -
Sparse representation for human gait recognition
by: Zeng, Zinan
Published: (2011) -
Weakly-supervised learning for video understanding
by: Deng, Dingfan
Published: (2023)