---
title: Aerial Imagery Semantic Segmentation
emoji: 🛰️
colorFrom: red
colorTo: gray
sdk: gradio
sdk_version: 6.20.0
app_file: app.py
short_description: Aerial semantic segmentation — CABiNet & YOLO26 models
python_version: "3.12"
startup_duration_timeout: 30m
pinned: false
---

# UAVid Semantic Segmentation — CABiNet & YOLO26 Model Zoo

Interactive demo of the [**UAVid Semantic Segmentation Model Zoo**](https://huggingface.co/collections/dronefreak/uavid-semantic-segmentation-model-zoo) —
pick any model from the dropdown and run it on an oblique aerial / drone urban scene, trained on
the [UAVid](https://uavid.nl/) benchmark:

| Model | mIoU (%) | Params (M) | FLOPs (GFLOPs) | HF Weights |
| --- | --- | --- | --- | --- |
| CABiNet (MobileNetV3-Large) | 68.60 | 9.17 | 54.8 | [link](https://huggingface.co/dronefreak/cabinet-mobilenetv3-large-uavid) |
| CABiNet (MobileNetV3-Small) | 66.84 | 5.36 | 44.1 | [link](https://huggingface.co/dronefreak/cabinet-mobilenetv3-small-uavid) |
| YOLO26x-sem | 64.41 | 40.16 | 430.9 | [link](https://huggingface.co/dronefreak/uavid-yolo26x-sem) |
| YOLO26l-sem | 63.28 | 17.87 | 192.4 | [link](https://huggingface.co/dronefreak/uavid-yolo26l-sem) |
| YOLO26m-sem | 61.98 | 14.32 | 152.3 | [link](https://huggingface.co/dronefreak/uavid-yolo26m-sem) |
| YOLO26s-sem | 61.69 | 6.50 | 44.4 | [link](https://huggingface.co/dronefreak/uavid-yolo26s-sem) |
| YOLO26n-sem | 58.17 | 1.63 | 11.4 | [link](https://huggingface.co/dronefreak/uavid-yolo26n-sem) |

**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.

Every pixel is classified into one of 8 classes: Clutter, Building, Road, Static Car, Tree,
Vegetation, Human, Moving Car. The demo renders a colored overlay and a per-class legend for
whichever model you select.

Example images are real UAVid validation frames from
[`dronefreak/UAVid-2020`](https://huggingface.co/datasets/dronefreak/UAVid-2020).

Runs on ZeroGPU.