{"url":"/dataset/hephaestus","name":"Hephaestus","full_name":"Hephaestus: A large scale multitask dataset towards InSAR understanding","description_markdown":"Hephaestus is the first large-scale InSAR dataset. Driven by volcanic unrest detection, it provides 19,919 unique satellite frames annotated with a diverse set of labels. Moreover, each sample is accompanied by a textual description of its contents. The goal of this dataset is to boost research on exploitation of interferometric data enabling the application of state-of-the-art computer vision+NLP methods. Furthermore, the annotated dataset is bundled with a large archive of unlabeled frames to enable large-scale self-supervised learning. The final size of the dataset amounts to 110,573 interferograms.","description_withheld":null,"homepage":"https://github.com/Orion-AI-Lab/Hephaestus","introduced_date":"2022-04-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/hephaestus-a-large-scale-multitask-dataset","title":"Hephaestus: A large scale multitask dataset towards InSAR understanding","first_author":"Nikolaos Ioannis Bountos","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Image Quality Assessment","url":"/task/image-quality-assessment","datasets_with_task":"/datasets/task/image-quality-assessment"}],"languages":[],"variants":["Hephaestus"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}