BriefGPT.xyz
Nov, 2022
SSL4EO-S12: 大规模多模态、多时相的自监督学习地球观测数据集
SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation
HTML
PDF
Yi Wang, Nassim Ait Ali Braham, Zhitong Xiong, Chenying Liu, Conrad M Albrecht...
TL;DR
使用自监督学习的方式对遥感数据进行预处理，能够形成高质量的可用于计算机视觉应用的表示。
Abstract
Self-supervised
pre-training
bears potential to generate expressive representations without human annotation. Most
pre-training
in
earth observat
→