---
license: etalab-2.0
pipeline_tag: image-segmentation
tags:
- semantic segmentation
- pytorch
- landcover
model-index:
- name: FLAIR-HUB_LC-I_swinbase-upernet
results:
- task:
type: semantic-segmentation
dataset:
name: IGNF/FLAIR-HUB/
type: earth-observation-dataset
metrics:
- type: mIoU
value: 43.488
name: mIoU
- type: OA
value: 64.126
name: Overall Accuracy
- type: IoU
value: 57.225
name: IoU building
- type: IoU
value: 49.833
name: IoU greenhouse
- type: IoU
value: 61.59
name: IoU swimming pool
- type: IoU
value: 53.178
name: IoU impervious surface
- type: IoU
value: 39.981
name: IoU pervious surface
- type: IoU
value: 43.96
name: IoU bare soil
- type: IoU
value: 71.021
name: IoU water
- type: IoU
value: 61.981
name: IoU snow
- type: IoU
value: 36.862
name: IoU herbaceous vegetation
- type: IoU
value: 48.208
name: IoU agricultural land
- type: IoU
value: 4.559
name: IoU plowed land
- type: IoU
value: 42.06
name: IoU vineyard
- type: IoU
value: 58.671
name: IoU deciduous
- type: IoU
value: 52.946
name: IoU coniferous
- type: IoU
value: 18.069
name: IoU brushwood
library_name: pytorch-lightning
---
π FLAIR-HUB Model Collection
-
Trained on: FLAIR-HUB dataset
π
-
Available modalities: Aerial images, SPOT images, Topographic info, Sentinel-2 yearly time-series, Sentinel-1 yearly time-series, Historical aerial images
-
Encoders: ConvNeXTV2, Swin (Tiny, Small, Base, Large)
-
Decoders: UNet, UPerNet
-
Tasks: Land-cover mapping (LC), Crop-type mapping (LPIS)
-
Class nomenclature: 15 classes for LC, 23 classes for LPIS
π
Model ID |
πΊοΈ
Land-cover |
πΎ
Crop-types |
π©οΈ
Aerial |
β°οΈ
Elevation |
π°οΈ
SPOT |
π°οΈ
S2 t.s. |
π°οΈ
S1 t.s. |
π©οΈ
Historical |
| LC-A |
β |
|
β |
|
|
|
|
|
| LC-D |
β |
|
β |
|
|
β |
|
|
| LC-F |
β |
|
β |
|
|
β |
β |
|
| LC-G |
β |
|
|
|
|
β |
|
|
| LC-I |
β |
|
|
|
β |
|
|
|
| LC-L |
β |
|
β |
β |
β |
β |
β |
|
| LPIS-A |
|
β |
β |
|
|
|
|
|
| LPIS-F |
|
β |
|
|
|
β |
|
|
| LPIS-I |
|
β |
|
|
β |
β |
β |
|
| LPIS-J |
|
β |
β |
|
β |
β |
β |
|
π Model: FLAIR-HUB_LC-I_swinbase-upernet
-
Encoder: swin_base_patch4_window12_384
-
Decoder: upernet
-
Metrics:
| mIoU |
O.A. |
F-score |
Precision |
Recall |
| 43.49% |
64.13% |
58.09% |
59.34% |
58.11% |
-
Params.: 89.2
---
## General Informations
- **Contact:** flair@ign.fr
- **Code repository:** https://github.com/IGNF/FLAIR-HUB
- **Paper:** https://arxiv.org/abs/2506.07080
- **Developed by:** IGN
- **Compute infrastructure:**
- software: python, pytorch-lightning
- hardware: HPC/AI resources provided by GENCI-IDRIS
- **License:** Etalab 2.0
---
### Training Config Hyperparameters
```yaml
- Model architecture: swin_base_patch4_window12_384-upernet
- Optimizer: AdamW (betas=[0.9, 0.999], weight_decay=0.01)
- Learning rate: 5e-5
- Scheduler: one_cycle_lr (warmup_fraction=0.2)
- Epochs: 150
- Batch size: 5
- Seed: 2025
- Early stopping: patience 20, monitor val_miou (mode=max)
- Class weights:
- default: 1.0
- masked classes: [clear cut, ligneous, mixed, other] β weight = 0
- Input channels:
- SPOT_RGBI : [4,1,2]
- Input normalization (custom):
- SPOT_RGBI:
mean: [1137.09, 433.26, 508.75]
std: [543.11, 312.76, 284.61]
```
---
### Training Data
```yaml
- Train patches: 152225
- Validation patches: 38175
- Test patches: 50700
```
---
### Training Logging
---
## Metrics
| Metric | Value |
| ---------------- | ------ |
| mIoU | 43.49% |
| Overall Accuracy | 64.13% |
| F-score | 58.09% |
| Precision | 59.34% |
| Recall | 58.11% |
| Class | IoU (%) | F-score (%) | Precision (%) | Recall (%) |
| --------------------- | ------- | ----------- | ------------- | ---------- |
| building | 57.23 | 72.79 | 72.23 | 73.37 |
| greenhouse | 49.83 | 66.52 | 64.05 | 69.18 |
| swimming pool | 13.76 | 24.20 | 39.65 | 17.41 |
| impervious surface | 53.18 | 69.43 | 68.13 | 70.78 |
| pervious surface | 39.98 | 57.12 | 56.88 | 57.37 |
| bare soil | 43.96 | 61.07 | 63.87 | 58.51 |
| water | 71.02 | 83.06 | 80.41 | 85.88 |
| snow | 61.98 | 76.53 | 69.44 | 85.23 |
| herbaceous vegetation | 36.86 | 53.87 | 56.88 | 51.16 |
| agricultural land | 48.21 | 65.05 | 57.30 | 75.23 |
| plowed land | 4.56 | 8.72 | 12.45 | 6.71 |
| vineyard | 42.06 | 59.21 | 69.71 | 51.47 |
| deciduous | 58.67 | 73.95 | 73.26 | 74.66 |
| coniferous | 52.95 | 69.23 | 71.47 | 67.14 |
| brushwood | 18.07 | 30.61 | 34.41 | 27.56 |
---
## Inference
Aerial ROI
Inference ROI
---
## Cite
**BibTeX:**
```
@article{ign2025flairhub,
doi = {10.48550/arXiv.2506.07080},
url = {https://arxiv.org/abs/2506.07080},
author = {Garioud, Anatol and Giordano, SΓ©bastien and David, Nicolas and Gonthier, Nicolas},
title = {FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping},
publisher = {arXiv},
year = {2025}
}
```
**APA:**
```
Anatol Garioud, SΓ©bastien Giordano, Nicolas David, Nicolas Gonthier.
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping. (2025).
DOI: https://doi.org/10.48550/arXiv.2506.07080
```
