Research map / Detection and segmentation / Open-set and few-shot detection
FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery
Anatol Garioud, Nicolas Gonthier, Loic Landrieu, Apolline De Wit, Marion Valette, Marc Poupée, Sebastien Giordano, Boris Wattrelos
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Sentinel-2 time series branch (U-T&T) to aerial U-Net, without augmentations (ablation) | U-Net · FLAIR test | mIoU: 54.7 -> 54.9 | No clear effect |
| use satellite time series only (upsampled) instead of aerial imagery (ablation) | U-TAE · FLAIR test | mIoU: 54.7 -> 36.1 | Hurt |
| add all enhancements (FILT, AVG M, MTD, AUG) to U-T&T (ablation) | U-T&T · FLAIR test | mIoU: 54.9 -> 56.9 | Improved |
| add cloud/snow filtering of satellite images (ablation) | U-T&T · FLAIR test | mIoU: 54.9 -> 55.2 | Improved |
| add monthly averaging of cloudless satellite acquisitions (ablation) | U-T&T · FLAIR test | mIoU: 54.9 -> 55.0 | No clear effect |
| add metadata encoding (ablation) | U-T&T · FLAIR test | mIoU: 54.9 -> 54.9 | No clear effect |
| add geometric augmentation on aerial images (ablation) | U-T&T · FLAIR test | mIoU: 54.9 -> 55.5 | Improved |
| add satellite time series to U-Net (best runs) (ablation) | U-Net · FLAIR test per-class IoU | IoU: 54.7 -> 58.6 (best runs); bare soil 30.8 -> 43.7 | Improved |
| replace U-Net decoder with DeepLabV3 in aerial branch, with enhancements (ablation) | U-T&T · FLAIR test | mIoU: 56.9 -> 57.3 | Improved |
| replace U-Net decoder with FPN in aerial branch, with enhancements (ablation) | U-T&T · FLAIR test | mIoU: 56.9 -> 56.2 | Hurt |
Closest papers by meaning
- SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagery (AAAI 2026 · similarity 0.85)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.85)
- Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation (AAAI 2025 · similarity 0.84)
- OAM-TCD: A globally diverse dataset of high-resolution tree cover maps (NeurIPS 2024 · similarity 0.84)
- Fields of The World: A Machine Learning Benchmark Dataset for Global Agricultural Field Boundary Segmentation (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
