UAVid Semantic Segmentation — CABiNet & YOLO26 Model Zoo

Pick any model from the UAVid Semantic Segmentation Model Zoo — CABiNet (custom dual-branch PyTorch) or Ultralytics YOLO26 (n/s/m/l/x) — all fine-tuned on UAVid to label every pixel of an oblique drone / aerial urban scene into 8 classes: Clutter, Building, Road, Static Car, Tree, Vegetation, Human, Moving Car.

CABiNet (MobileNetV3-Large) is the top performer — it beats every YOLO26 variant, including the largest (YOLO26x), on mIoU while using a fraction of the compute.

Upload an aerial street-scene image (or try an example) to get a colored segmentation overlay.