Self-Supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

Self-Supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

Traditional self-supervised learning requires convolutional neural networks (CNNs) using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformations within CNNs can also be regarded as supervisor...

Full description

Bibliographic Details
Main Authors: Tianshu Xie, Yuhang Yang, Zilin Ding, Xuan Cheng, Xiaomin Wang, Haigang Gong, Ming Liu
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Deep learning
classification
self-supervised learning
convolutional neural network
feature transformation
Online Access:https://ieeexplore.ieee.org/document/10003201/

Internet

https://ieeexplore.ieee.org/document/10003201/

Similar Items