Mixup Feature: A Pretext Task Self-Supervised Learning Method for Enhanced Visual Feature Learning
Self-supervised learning has emerged as an increasingly popular research topic within the field of computer vision. In this study, we propose a novel self-supervised learning approach based on Mixup features as pretext tasks. The proposed method aims to learn visual representations by predicting the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Jezik: | English |
| Izdano: |
IEEE
2023-01-01
|
| Serija: | IEEE Access |
| Teme: | |
| Online dostop: | https://ieeexplore.ieee.org/document/10207028/ |