{"url":"/dataset/uavid","name":"UAVid","full_name":null,"description_markdown":"UAVid is a high-resolution UAV semantic segmentation dataset as a complement, which brings new challenges, including large scale variation, moving object recognition and temporal consistency preservation. The UAV dataset consists of 30 video sequences capturing 4K high-resolution images in slanted views. In total, 300 images have been densely labeled with 8 classes for the semantic labeling task. \r\n\r\nSource: [UAVid: A Semantic Segmentation Dataset for UAV Imagery](/paper/the-uavid-dataset-for-video-semantic)\r\nImage Source: [https://uavid.nl/](https://uavid.nl/)","description_withheld":null,"homepage":"https://uavid.nl/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-uavid-dataset-for-video-semantic","title":"UAVid: A Semantic Segmentation Dataset for UAV Imagery","first_author":"Ye Lyu","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Scene Understanding","url":"/task/scene-understanding","datasets_with_task":"/datasets/task/scene-understanding"},{"name":"Scene Segmentation","url":"/task/scene-segmentation","datasets_with_task":"/datasets/task/scene-segmentation"},{"name":"Autonomous Driving","url":"/task/autonomous-driving","datasets_with_task":"/datasets/task/autonomous-driving"}],"languages":[],"variants":["UAVid"],"data_loaders":[{"repo":"https://github.com/WangLibo1995/GeoSeg","url":"https://www.sciencedirect.com/science/article/abs/pii/S0924271622001654","frameworks":["pytorch"]}],"num_papers_in_archive":54,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-uavid","task":"Semantic Segmentation","dataset_variant":"UAVid","rows":10,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"U-Net Ensemble","paper":"/paper/u-net-ensemble-for-enhanced-semantic","metrics":{"Mean IoU":"73.34"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-segmentation-on-uavid","task":"Scene Segmentation","dataset_variant":"UAVid","rows":1,"metrics":["Category mIoU"],"first_row_in_archive_order":{"model":"UNetFormer","paper":"/paper/efficient-hybrid-transformer-learning-global","metrics":{"Category mIoU":"67.8"},"code_links":[{"title":"WangLibo1995/GeoSeg","url":"https://github.com/WangLibo1995/GeoSeg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dynamic-dictionary-learning-for-remote","title":"Dynamic Dictionary Learning for Remote Sensing Image Segmentation","date":"2025-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":9,"samples_unverified":3,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lwganet-a-lightweight-group-attention","title":"LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks","date":"2025-01-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decouplenet-a-lightweight-backbone-network","title":"DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks","date":"2024-09-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sfa-net-semantic-feature-adjustment-network","title":"SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation","date":"2024-09-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/u-net-ensemble-for-enhanced-semantic","title":"U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery","date":"2024-06-08","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","date":"2024-03-18","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/efficient-hybrid-transformer-learning-global","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","date":"2021-09-18","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transformer-meets-convolution-a-bilateral","title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","date":"2021-06-23","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":14,"samples_ran":11,"samples_unverified":3,"pointer_only_for_licence":14,"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."}