{"url":"/dataset/second","name":"SECOND","full_name":"SEmantic Change detectiON Dataset","description_markdown":"SECOND is a well-annotated semantic change detection dataset. To ensure data diversity, we firstly collect 4662 pairs of aerial images from several platforms and sensors. These pairs of images are distributed over the cities such as Hangzhou, Chengdu, and Shanghai. Each image has size 512 x 512 and is annotated at the pixel level. The annotation of SECOND is carried out by an expert group of earth vision applications, which guarantees high label accuracy. For the change category in the SECOND dataset, we focus on 6 main land-cover classes, i.e. , non-vegetated ground surface, tree, low vegetation, water, buildings and playgrounds , that are frequently involved in natural and man-made geographical changes. It is worth noticing that, in the new dataset, non-vegetated ground surface ( n.v.g. surface for short) mainly corresponds to impervious surface and bare land. In summary, these 6 selected land-cover categories result in 30 common change categories (including non-change ). Through the random selection of image pairs, the SECOND reflects real distributions of land-cover categories when changes occur.","description_withheld":null,"homepage":"https://captain-whu.github.io/SCD/","introduced_date":"2020-10-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/asymmetric-siamese-networks-for-semantic","title":"Semantic Change Detection with Asymmetric Siamese Networks","first_author":"Kunping Yang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Change Detection","url":"/task/change-detection","datasets_with_task":"/datasets/task/change-detection"},{"name":"Building change detection for remote sensing images","url":"/task/building-change-detection-for-remote-sensing","datasets_with_task":"/datasets/task/building-change-detection-for-remote-sensing"},{"name":"Change detection for remote sensing images","url":"/task/change-detection-for-remote-sensing-images","datasets_with_task":"/datasets/task/change-detection-for-remote-sensing-images"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SECOND"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/change-detection-on-second","task":"Change Detection","dataset_variant":"SECOND","rows":2,"metrics":["SeK","Fscd","mIoU"],"first_row_in_archive_order":{"model":"ChangeMamba","paper":"/paper/changemamba-remote-sensing-change-detection","metrics":{"Fscd":"64.03","SeK":"24.11","mIoU":"73.68"},"code_links":[{"title":"chenhongruixuan/mambacd","url":"https://github.com/chenhongruixuan/mambacd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/changemamba-remote-sensing-change-detection","title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","date":"2024-04-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/joint-spatio-temporal-modeling-for-semantic","title":"Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images","date":"2022-12-10","rows_on_this_dataset":1,"code_links":3,"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."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":2,"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."}