Mask R-CNN ResNet50 FPN - COCO Instance Segmentation
An established class-aware instance segmentation baseline that predicts a box and a mask for each detected object. Adapt the COCO checkpoint before mapping custom GIS assets.
Tag collection
GeoAI
Explore published GISSchools content associated with this exact Tag.
30published resources
Exact Tag results
Resources tagged GeoAI
Showing only published content with this exact existing Tag relationship.
SAM 2.1 Hiera Tiny - Promptable Instance Masks
Use points or boxes to extract individual object masks. SAM 2.1 supports interactive image segmentation and video object tracking, without assigning semantic class names.
ViT Base Patch16 - ImageNet Image Classification
A patch-based Transformer counterpart to ResNet. Explore whole-image classification, transfer learning and the difference between image labels and mapped land cover.
ResNet-18 - ImageNet Image Classification
An accessible residual-network baseline for whole-image classification. Includes the genuine provider checkpoint, configuration and processor for a reproducible starting point.
DeepLabV3 ResNet50 - Semantic Segmentation
The official TorchVision DeepLabV3 ResNet50 checkpoint provides a convolutional counterpart to SegFormer. Learn atrous context, pixel masks and the fine-tuning needed for GIS cl…
SegFormer B0 - ADE20K Semantic Segmentation
A real ADE20K-finetuned SegFormer B0 checkpoint for semantic pixel labeling. Explore its encoder/decoder workflow and the limits of using scene-parsing weights on satellite imag…
RT-DETR R18vd - COCO Object Detection
An official RT-DETR R18vd checkpoint with a CNN backbone and Transformer decoder. Includes genuine local safetensors weights, configuration and source attribution.
YOLO26n - COCO Object Detection
A compact official YOLO26 detector for RGB images. Learn its box outputs, custom training workflow and the steps needed before applying COCO weights to aerial imagery.