README.md

---
license: agpl-3.0

pipeline_tag: image-segmentation

library_name: ultralytics

base_model: "Ultralytics/YOLO26"

tags:
  - semantic-segmentation
  - aerial-imagery
  - drone
  - uavid
  - yolo26
  - ultralytics
  - pytorch
  - computer-vision
datasets:
  - dronefreak/UAVid-2020
metrics:
  - miou
  - pixel-accuracy
---

# YOLO26s-sem Finetuned on UAVid

![License](https://img.shields.io/badge/License-AGPL--3.0-1f6feb?style=flat-square) ![Framework](https://img.shields.io/badge/Framework-Ultralytics-6a5acd?style=flat-square) ![Dataset](https://img.shields.io/badge/Dataset-UAVid-0aa1a7?style=flat-square) ![mIoU](https://img.shields.io/badge/mIoU-61.69%25-e8a33d?style=flat-square) ![Status](https://img.shields.io/badge/Status-Trained-2ea44f?style=flat-square) ![Maintained](https://img.shields.io/badge/Maintained-yes-17a2b8?style=flat-square)

Fine-tuned YOLO26s semantic segmentation model for aerial UAV imagery using the UAVid benchmark dataset.

This model is part of the **UAVid Semantic Segmentation Model Zoo**, a collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation.


<p align="center">
  <img src="uavid_showcase.gif" alt="UAVid Semantic Segmentation Demo">
</p>

---

## Performance

| Metric              | Score           |
| ------------------- | --------------- |
| mIoU                | 61.69      |
| Pixel Accuracy      | 84.27 |
| Parameters (M)      | 6.50    |
| FLOPs (GFLOPs @ 1024px) | 44.4     |

---

## UAVid Model Zoo

| Rank | Model                | mIoU (%)      | Pixel Acc (%)      | Params (M)        | FLOPs (GFLOPs)    |
| ---- | --------------------- | ------------- | ------------------ | ----------------- | ----------------- |
| 1    | CABiNet (MobileNetV3-Large) | 68.6 | 87.31 | 9.17 | 54.8 |
| 2    | CABiNet (MobileNetV3-Small) | 66.84 | 86.45 | 5.36 | 44.1 |
| 3    | YOLO26x-sem | 64.41 | 85.82 | 40.16 | 430.9 |
| 4    | YOLO26l-sem | 63.28 | 84.75 | 17.87 | 192.4 |
| 5    | YOLO26m-sem | 61.98 | 84.41 | 14.32 | 152.3 |
| 6    | YOLO26s-sem | 61.69 | 84.27 | 6.50 | 44.4 |
| 7    | YOLO26n-sem | 58.17 | 82.31 | 1.63 | 11.4 |

---

## Per-Class IoU (%)

| Class | CABiNet (MobileNetV3-Large) | CABiNet (MobileNetV3-Small) | YOLO26x-sem | YOLO26l-sem | YOLO26m-sem | YOLO26s-sem | YOLO26n-sem | 
| --- | --- | --- | --- | --- | --- | --- | --- | 
| Clutter | 69.37 | 67.96 | 67.34 | 65.63 | 64.63 | 63.8 | 61.46 | 
| Building | 87.77 | 86.59 | 87.37 | 85.9 | 86.1 | 85.01 | 82.29 | 
| Road | 81.62 | 80.94 | 79.82 | 78.87 | 78.61 | 78.14 | 75.25 | 
| Static Car | 59.3 | 55.69 | 51.33 | 54.48 | 44.74 | 47.39 | 41.08 | 
| Tree | 81.23 | 80.09 | 78.19 | 76.68 | 76.44 | 76.8 | 74.06 | 
| Vegetation | 65.88 | 64.12 | 63.3 | 59.97 | 60.07 | 60.25 | 55.65 | 
| Human | 30.04 | 27.32 | 21.09 | 19.34 | 20.41 | 18.88 | 15.82 | 
| Moving Car | 73.62 | 71.99 | 66.81 | 65.38 | 64.88 | 63.3 | 59.73 | 

---

## Evaluation Visualizations

### Per-Class IoU Bar Chart

![IoU Bar Chart](iou_bar_chart.png)

### Confusion Matrix

![Confusion Matrix](confusion_matrix_normalized.png)

### Loss Curves

![Loss Curves](results.png)

---

## Dataset

[UAVid](https://uavid.nl/) is a high-resolution UAV semantic segmentation benchmark of urban street scenes, captured from oblique aerial viewpoints along street-side flight paths.

### Classes

- Clutter
- Building
- Road
- Static Car
- Tree
- Vegetation
- Human
- Moving Car

---

## Usage

### Install Dependencies

```bash
pip install ultralytics huggingface_hub
```

### Load Model from Hugging Face

```python
from huggingface_hub import hf_hub_download
from ultralytics import YOLO

weights = hf_hub_download(
    repo_id="dronefreak/uavid-yolo26s-sem",
    filename="best.pt"
)

model = YOLO(weights)
```

### Run Inference

```python
results = model.predict(source="image.png", task="semantic", imgsz=1024)
mask = results[0].semantic_mask.cpu().numpy().data  # (H, W) class-ID map
```

---

## Training Configuration

| Setting     | Value                                    |
| ------------ | ------------------------------------------ |
| Epochs       | 500                       |
| Image size   | 1024                        |
| Batch size   | 8                   |
| Dataset      | UAVid (converted images/+masks/ format)    |
| Framework    | Ultralytics YOLO                       |
| cls_pw (class weighting) | 0.5          |

---

## Official Resources

- **UAVid Semantic Segmentation Model Zoo:** https://huggingface.co/collections/dronefreak/uavid-semantic-segmentation-model-zoo
- **CABiNet repository:** https://github.com/dronefreak/CABiNet
- **CABiNet Paper:** https://arxiv.org/abs/2011.00993v2
- **Official UAVid Website:** https://uavid.nl/
- **UAVid Dataset Archive:** https://doi.org/10.17026/dans-x9f-w9sa
- **UAVid Paper:** https://arxiv.org/abs/1810.10438
- **UAVid Published Journal:** https://doi.org/10.1016/j.isprsjprs.2020.05.009
- **Ultralytics YOLO:** https://github.com/ultralytics/ultralytics
- **Ultralytics YOLO26 Paper:** https://arxiv.org/abs/2606.03748

---

## Training Framework

Trained with the [CABiNet repository](https://github.com/dronefreak/CABiNet), which pairs its own real-time segmentation trainer with a parallel Ultralytics YOLO26-sem pipeline — shared UAVid dataset tooling, training/eval, and mIoU benchmarking across both. Star the repo if you find these models useful!

---

## Known Limitations

Performance may degrade in:

* Very small or thin objects (e.g. pedestrians, moving cars at altitude)
* Heavy occlusion under tree canopy
* Motion blur on moving vehicles
* Mixed/very high input resolutions (UAVid source images are 3840x2160 / 4096x2160; both pipelines evaluate at reduced imgsz)

---

## Citation

Please cite the following:

```bibtex

@article{LYU2020108,
    author = "Ye Lyu and George Vosselman and Gui-Song Xia and Alper Yilmaz and Michael Ying Yang",
    title = "UAVid: A semantic segmentation dataset for UAV imagery",
    journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
    volume = "165",
    pages = "108 - 119",
    year = "2020",
    issn = "0924-2716",
    doi = "https://doi.org/10.1016/j.isprsjprs.2020.05.009",
    url = "http://www.sciencedirect.com/science/article/pii/S0924271620301295",
}

@INPROCEEDINGS{9560977,
  author={Kumaar, Saumya and Lyu, Ye and Nex, Francesco and Yang, Michael Ying},
  booktitle={2021 IEEE International Conference on Robotics and Automation (ICRA)},
  title={CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation},
  year={2021},
  pages={13517-13524},
  doi={10.1109/ICRA48506.2021.9560977}
}

@article{Kumaar_Real-time_Semantic_Segmentation_2021,
author = {Kumaar, Saumya and Lyu, Ye and Nex, Francesco and Yang, Michael Ying},
doi = {10.1016/j.isprsjprs.2021.06.006},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
pages = {124--134},
title = {{Real-time Semantic Segmentation with Context Aggregation Network}},
url = {https://www.sciencedirect.com/science/article/pii/S0924271621001647},
volume = {178},
year = {2021}
}

@article{jocher2026ultralytics,
  title={Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models},
  author={Jocher, Glenn and Qiu, Jing and Liu, Mengyu and Lyu, Shuai and Akyon, Fatih Cagatay and Kalfaoglu, Muhammet Esat},
  journal={arXiv preprint arXiv:2606.03748},
  year={2026}
}

@software{cabinet_uavid_benchmark,
  author = {Kumaar, Saumya},
  title = {CABiNet: Semantic Segmentation Benchmarking on UAVid (CABiNet vs. YOLO26)},
  url = {https://github.com/dronefreak/CABiNet},
  year = {2026}
}
```