Transformers

Here you can find models for typical remote sensing tasks that demonstrate a novel rotated varied-size window attention method to advance the performance of plain vision transformers.

This repository contains references to more than 60 recent transformers-based methods for different remote sensing problems and will be updated and maintained to include the latest transformers.

Transformers have achieved state of the art performance on remote sensing classification datasets and look set to make an impact on other common tasks such as segmentation and object detection.