# Remote Sensing Image Analysis

A multi-label image classification model fine-tuned based on SigLIP architecture, capable of identifying 7 types of geographic scene elements

A semantic segmentation model fine-tuned on satellite image datasets based on NVIDIA SegFormer-B0 architecture, specifically designed for earthquake-related scenario analysis

A YOLOv5m-based aerial sheep object detection model, specifically designed for detecting sheep in aerial images.

This model is a fine-tuned image classification model based on Google's ViT-base-patch16-224-in21k on a rock glacier dataset, achieving an accuracy of 92.58%.

A fine-tuned image classification model based on Swin Transformer architecture, achieving 95.17% accuracy on image classification tasks

This is a tiny model based on the Swin Transformer architecture, specifically designed for image classification tasks and fine-tuned on the EuroSAT dataset.