A decoupled learning framework for contrastive learning
Contrastive Learning (CL) has attracted much attention in recent years because various self-supervised models based on CL achieve comparable performance to supervised models. Nevertheless, most CL frameworks require large batch size during the training progress for taking more negative samples in...
Saved in:
Main Author: | Xu, Yicheng |
---|---|
Other Authors: | Lin Zhiping |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/163711 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Graph contrastive learning
by: Tran, Nguyen Manh Thien
Published: (2023) -
Efficient learning through biological neural network-Hebbian learning
by: Zhou, Yanpeng
Published: (2022) -
Tactile identification of fruits using machine learning/deep learning
by: Kua, Jia Kang
Published: (2023) -
Smart learning
by: Chan, Jerome Chun Hou
Published: (2020) -
Sequential learning for extreme learning machine
by: Liang, Nanying
Published: (2008)