<bold>TOV:</bold> <bold>T</bold>he <bold>O</bold>riginal <bold>V</bold>ision Model for Optical Remote Sensing Image Understanding via Self-Supervised Learning

<bold>TOV:</bold> <bold>T</bold>he <bold>O</bold>riginal <bold>V</bold>ision Model for Optical Remote Sensing Image Understanding via Self-Supervised Learning

Are we on the right way for remote sensing image understanding (RSIU) by training models in a supervised data-dependent and task-dependent manner, instead of original human vision in a label-free and task-independent way? We argue that a more desirable RSIU model should be trained with intrinsic str...

Full description

Bibliographic Details
Main Authors: Chao Tao, Ji Qi, Guo Zhang, Qing Zhu, Weipeng Lu, Haifeng Li
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Human vision
original vision model
pretraining models
remote sensing image understanding (RSIU)
self-supervised learning (SSL)
Online Access:https://ieeexplore.ieee.org/document/10110958/

Internet

https://ieeexplore.ieee.org/document/10110958/

Similar Items