⚠️Important Notice: The pre-trained model weight and pre-training code are only available for the non-commercial research. For any commercial use or cooperation, please contact Yansheng Li at Wuhan University (e-mail: yansheng.li@whu.edu.cn).

🌍SkySense++ Weights for few-shot inference:

🔗SkySense++ [OneDrive] [BaiduDisk]

🌍SkySense++ Weights in OpenMMLab format for finetuning:

🔗SkySense++ Backbone HR OpenMMLab Format [OneDrive] [BaiduDisk]

🔗SkySense++ Backbone S2 OpenMMLab Format [OneDrive] [BaiduDisk]

🔗SkySense++ Backbone S1 OpenMMLab Format [OneDrive] [BaiduDisk]

🌍SkySense Weights:

🔗SkySense Backbone HR [OneDrive] [BaiduDisk]

🔗SkySense Backbone S2 [OneDrive] [BaiduDisk]

🔗SkySense Backbone S1 [OneDrive] [BaiduDisk]

🔗SkySense Head S2 [OneDrive] [BaiduDisk]

🔗SkySense Head S1 [OneDrive] [BaiduDisk]

🔗SkySense Fusion [OneDrive] [BaiduDisk]

📊 Files for evaluation：

🛰Flood3i：

Images/Semantic_mask

val.txt

🌳Atlantic：

https://github.com/davej23/attention-mechanism-unet

deforestation_atlantic_train.json

deforestation_atlantic_val.json

deforestation_atlantic_test.json