Advancing Multi-Scale Remote Sensing Analysis Through Self-Supervised Learning Fine-Tuning Strategies

This research focuses on improving the fine-tuning process of self-supervised learning models for remote sensing, particularly the Cross-Scale Masked Auto-Encoder (MAE). We tackle the challenges of intricate, multi-source imagery and present advancements in adapting the Cross-Scale MAE for diverse r...

Full description

Saved in:
Bibliographic Details
Main Authors: Georgiou, Konstantinos, Tang, Maofeng, Wang, Fanqi, Tang, Weisheng, Qi, Hairong, Champion, Cody, Bosch, Marc
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Analytical models
Masked Image Modeling
Remote sensing
Self-supervised learning
Semantics
transfer learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This research focuses on improving the fine-tuning process of self-supervised learning models for remote sensing, particularly the Cross-Scale Masked Auto-Encoder (MAE). We tackle the challenges of intricate, multi-source imagery and present advancements in adapting the Cross-Scale MAE for diverse remote sensing environments. Our contributions include methods for handling complex dataset dimensions and semantic diversity, demonstrating the model's adaptability and expanding its application scope in remote sensing.
ISSN:2153-7003
DOI:10.1109/IGARSS53475.2024.10642908