{"url":"/dataset/inria-aerial-image-labeling","name":"INRIA Aerial Image Labeling","full_name":"INRIA Aerial Image Labeling","description_markdown":"The **INRIA Aerial Image Labeling** dataset is comprised of 360 RGB tiles of 5000×5000px with a spatial resolution of 30cm/px on 10 cities across the globe. Half of the cities are used for training and are associated to a public ground truth of building footprints. The rest of the dataset is used only for evaluation with a hidden ground truth. The dataset was constructed by combining public domain imagery and public domain official building footprints.\r\n\r\nSource: [Distance transform regression for spatially-aware deep semantic segmentation](https://arxiv.org/abs/1909.01671)\r\nImage Source: [https://project.inria.fr/aerialimagelabeling/](https://project.inria.fr/aerialimagelabeling/)","description_withheld":null,"homepage":"https://project.inria.fr/aerialimagelabeling/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/very-deep-convolutional-networks-for-large","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","first_author":"Karen Simonyan","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Contrastive Learning","url":"/task/contrastive-learning","datasets_with_task":"/datasets/task/contrastive-learning"}],"languages":[],"variants":["INRIA Aerial Image Labeling"],"data_loaders":[],"num_papers_in_archive":21,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-inria-aerial-image","task":"Semantic Segmentation","dataset_variant":"INRIA Aerial Image Labeling","rows":8,"metrics":["IoU","mIOU"],"first_row_in_archive_order":{"model":"UANet(PVT-V2-B2)","paper":"/paper/building-extraction-from-remote-sensing-1","metrics":{"IoU":"83.34"},"code_links":[{"title":"henryjiepanli/uncertainty-aware-network","url":"https://github.com/henryjiepanli/uncertainty-aware-network"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dsat-net-dual-spatial-attention-transformer","title":"DSAT-Net: Dual Spatial Attention Transformer for Building Extraction from Aerial Images","date":"2023-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/building-extraction-from-remote-sensing-1","title":"Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network","date":"2023-07-23","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/ultra-high-resolution-segmentation-with-ultra-1","title":"Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark","date":"2023-05-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sdsc-unet-dual-skip-connection-vit-based-u","title":"SDSC-UNet: Dual Skip Connection ViT-based U-shaped Model for Building Extraction","date":"2023-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-segmentation-from-remote-sensor-data","title":"Semantic Segmentation from Remote Sensor Data and the Exploitation of Latent Learning for Classification of Auxiliary Tasks","date":"2019-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}