ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing
Collection of research papers and implementations applying deep learning and vision transformers to remote sensing imagery analysis.

Velocity · 7d
+0.3
★ / day
Trend
→steady
star history
This repository aggregates multiple research works on remote sensing using deep learning approaches, including vision transformers (ViT), self-supervised pretraining, and segmentation models like SAM adapted for satellite/aerial imagery. It covers tasks such as change detection, object detection, semantic segmentation, and classification in geospatial contexts.