[CVPR 2019, Oral] "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images" by Wuyang Chen*, Ziyu Jiang*, Zhangyang Wang, Kexin Cui, and Xiaoning Qian
-
Updated
Dec 29, 2021 - Python
#
deepglobe
Here are 6 public repositories matching this topic...
DeepGlobe Land Cover Classification Challenge遥感影像语义分割
-
Updated
May 20, 2020 - Python
U-Net road segmentation pretrained on DeepGlobe and fine-tuned on UAVid (IoU 0.7168)
-
Updated
Jun 22, 2026 - Python
Lightweight U-Net for road segmentation from satellite images using the DeepGlobe dataset.
-
Updated
Jun 22, 2025 - Jupyter Notebook
Semantic segmentation of satellite and aerial imagery for land cover classification using U-Net + ResNet-50. Trained on DeepGlobe (7 classes, mIoU 0.637) and LandCover.ai (4 classes, mIoU 0.798). Includes interactive Gradio demo with confidence-based OOD detection and class distribution visualization.
computer-vision deep-learning pytorch kaggle remote-sensing unet gradio semantic-segmentation rasterio land-cover resnet-50 confidence deepglobe land-cover-classification torchmetrics
-
Updated
Jun 28, 2026 - Jupyter Notebook
Semantic segmentation of high-resolution satellite imagery on the DeepGlobe Land Cover dataset, comparing U-Net, DeepLabV3+, and DenseASPP under a controlled multi-scale context modeling framework.
computer-vision pytorch remote-sensing satellite-imagery unet semantic-segmentation deeplabv3 denseaspp deepglobe
-
Updated
Feb 4, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the deepglobe topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the deepglobe topic, visit your repo's landing page and select "manage topics."