CorrFractal: High-Resolution Correspondence Method Using Fractal Affinity on Self-Supervised Learning

CorrFractal: High-Resolution Correspondence Method Using Fractal Affinity on Self-Supervised Learning

Existing supervised learning-based methods performed high-resolution visual correspondence using a decoder module. However, in self-supervised learning-based methods, it is difficult to use a decoder module that is easily influenced by labels. This paper will introduce a self-supervised learning-bas...

Full description

Bibliographic Details
Main Authors: Jin-Mo Choi, Blagovest I. Vladimirov, Sangjoon Park
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Decoder module
high-resolution representation
pseudo labeling
self-supervised learning
visual correspondence
Online Access:https://ieeexplore.ieee.org/document/10403912/

Internet

https://ieeexplore.ieee.org/document/10403912/

Similar Items