7 datasets found
  1. P

    iSAID Dataset

    • paperswithcode.com
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Syed Waqas Zamir; Aditya Arora; Akshita Gupta; Salman Khan; Guolei Sun; Fahad Shahbaz Khan; Fan Zhu; Ling Shao; Gui-Song Xia; Xiang Bai, iSAID Dataset [Dataset]. https://paperswithcode.com/dataset/isaid
    Explore at:
    Authors
    Syed Waqas Zamir; Aditya Arora; Akshita Gupta; Salman Khan; Guolei Sun; Fahad Shahbaz Khan; Fan Zhu; Ling Shao; Gui-Song Xia; Xiang Bai
    Description

    iSAID contains 655,451 object instances for 15 categories across 2,806 high-resolution images. The images of iSAID is the same as the DOTA-v1.0 dataset, which are manily collected from the Google Earth, some are taken by satellite JL-1, the others are taken by satellite GF-2 of the China Centre for Resources Satellite Data and Application.

  2. f

    Semantic segmentation of the HSR remote sensing dataset iSAID dataset using...

    • plos.figshare.com
    bin
    Updated Jul 27, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Guangjie Liu; Qi Wang; Jinlong Zhu; Haotong Hong (2023). Semantic segmentation of the HSR remote sensing dataset iSAID dataset using state-of-the-art methods to compare the experimental mIoU. [Dataset]. http://doi.org/10.1371/journal.pone.0288311.t006
    Explore at:
    binAvailable download formats
    Unique identifier
    https://doi.org/10.1371/journal.pone.0288311.t006
    Dataset updated
    Jul 27, 2023
    Dataset provided by
    PLOS ONE
    Authors
    Guangjie Liu; Qi Wang; Jinlong Zhu; Haotong Hong
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    Semantic segmentation of the HSR remote sensing dataset iSAID dataset using state-of-the-art methods to compare the experimental mIoU.

  3. USAID - India

    • iatiregistry.org
    iati-xml
    Updated Mar 5, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    United States Agency for International Development (USAID) (2025). USAID - India [Dataset]. https://iatiregistry.org/dataset/usaid-in
    Explore at:
    iati-xml(7948407)Available download formats
    Dataset updated
    Mar 5, 2025
    Dataset provided by
    United States Agency for International Developmenthttps://usaid.gov/
    License

    CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
    License information was derived automatically

    Area covered
    India
    Description

    USAID - India

  4. Pretraining data of SkySense++

    • zenodo.org
    bin
    Updated Mar 18, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Kang Wu; Kang Wu (2025). Pretraining data of SkySense++ [Dataset]. http://doi.org/10.5281/zenodo.14994430
    Explore at:
    binAvailable download formats
    Unique identifier
    https://doi.org/10.5281/zenodo.14994430
    Dataset updated
    Mar 18, 2025
    Dataset provided by
    Zenodohttp://zenodo.org/
    Authors
    Kang Wu; Kang Wu
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Time period covered
    Mar 9, 2024
    Description

    This repository contains the data description and processing for the paper titled "SkySense++: A Semantic-Enhanced Multi-Modal Remote Sensing Foundation Model for Earth Observation." The code is in here

    📢 Latest Updates

    🔥🔥🔥 Last Updated on 2024.03.14 🔥🔥🔥

    Pretrain Data

    RS-Semantic Dataset

    We conduct semantic-enhanced pretraining on the RS-Semantic dataset, which consists of 13 datasets with pixel-level annotations. Below are the specifics of these datasets.

    DatasetModalitiesGSD(m)SizeCategoriesDownload Link
    Five Billion PixelsGaofen-246800x720024Download
    PotsdamAirborne0.056000x60005Download
    VaihingenAirborne0.052494x20645Download
    DeepglobeWorldView0.52448x24486Download
    iSAIDMultiple Sensors-800x800 to 4000x1300015Download
    LoveDASpaceborne0.31024x10247Download
    DynamicEarthNetWorldView0.31024x10247Download
    Sentinel-2*1032x32
    Sentinel-1*1032x33
    Pastis-MMWorldView0.31024x102418Download
    Sentinel-2*1032x32
    Sentinel-1*1032x33
    C2Seg-ABSentinel-2*10128x12813Download
    Sentinel-1*10128x128
    FLAIRSpot-50.2512x51212Download
    Sentinel-2*1040x40
    DFC20Sentinel-210256x2569Download
    Sentinel-110256x256
    S2-naipNAIP1512x51232Download
    Sentinel-2*1064x64
    Sentinel-1*1064x64
    JL-16Jilin-10.72512x51216Download
    Sentinel-1*1040x40

    * for time-series data.

    EO Benchmark

    We evaluate our SkySense++ on 12 typical Earth Observation (EO) tasks across 7 domains: agriculture, forestry, oceanography, atmosphere, biology, land surveying, and disaster management. The detailed information about the datasets used for evaluation is as follows.

    DomainTask typeDatasetModalitiesGSDImage sizeDownload LinkNotes
    AgricultureCrop classificationGermanySentinel-2*1024x24Download
    ForesetryTree species classificationTreeSatAI-Time-SeriesAirborne,0.2304x304Download
    Sentinel-2*106x6
    Sentinel-1*106x6
    Deforestation segmentationAtlanticSentinel-210512x512Download
    OceanographyOil spill segmentationSOSSentinel-110256x256Download
    AtmosphereAir pollution regression3pollutionSentinel-210200x200Download
    Sentinel-5P2600120x120
    BiologyWildlife detectionKenyaAirborne-3068x4603Download
    Land surveyingLULC mappingC2Seg-BWGaofen-610256x256Download
    Gaofen-310256x256
    Change detectiondsifn-cdGoogleEarth0.3512x512Download
    Disaster managementFlood monitoringFlood-3iAirborne0.05256 × 256Download
    C2SMSFloodsSentinel-2, Sentinel-110512x512Download
    Wildfire monitoringCABUARSentinel-2105490 × 5490Download
    Landslide mappingGVLMGoogleEarth0.31748x1748 ~ 10808x7424Download
    Building damage assessmentxBDWorldView0.31024x1024Download

    * for time-series data.

  5. isaid_class_14

    • kaggle.com
    Updated May 15, 2024
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Сергей Ворон (2024). isaid_class_14 [Dataset]. https://www.kaggle.com/datasets/serjvoron/isaid-class-14/code
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    May 15, 2024
    Dataset provided by
    Kagglehttp://kaggle.com/
    Authors
    Сергей Ворон
    Description

    Dataset

    This dataset was created by Сергей Ворон

    Contents

  6. f

    Accuracy (PA), precision (mIoU), and consistency (Kappa) obtained by testing...

    • plos.figshare.com
    bin
    Updated Jul 27, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Guangjie Liu; Qi Wang; Jinlong Zhu; Haotong Hong (2023). Accuracy (PA), precision (mIoU), and consistency (Kappa) obtained by testing using different backbones in the fully convolutional neural network (FCN). [Dataset]. http://doi.org/10.1371/journal.pone.0288311.t002
    Explore at:
    binAvailable download formats
    Unique identifier
    https://doi.org/10.1371/journal.pone.0288311.t002
    Dataset updated
    Jul 27, 2023
    Dataset provided by
    PLOS ONE
    Authors
    Guangjie Liu; Qi Wang; Jinlong Zhu; Haotong Hong
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    Accuracy (PA), precision (mIoU), and consistency (Kappa) obtained by testing using different backbones in the fully convolutional neural network (FCN).

  7. USAID Public Data Listing

    • catalog.data.gov
    Updated Jun 25, 2024
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    data.usaid.gov (2024). USAID Public Data Listing [Dataset]. https://catalog.data.gov/dataset/usaid-public-data-listing
    Explore at:
    Dataset updated
    Jun 25, 2024
    Dataset provided by
    United States Agency for International Developmenthttps://usaid.gov/
    Description

    This is Version 6.0, 20200130 of the catalog of publicly available USAID datasets

  8. Not seeing a result you expected?
    Learn how you can add new datasets to our index.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
Syed Waqas Zamir; Aditya Arora; Akshita Gupta; Salman Khan; Guolei Sun; Fahad Shahbaz Khan; Fan Zhu; Ling Shao; Gui-Song Xia; Xiang Bai, iSAID Dataset [Dataset]. https://paperswithcode.com/dataset/isaid

iSAID Dataset

Explore at:
Authors
Syed Waqas Zamir; Aditya Arora; Akshita Gupta; Salman Khan; Guolei Sun; Fahad Shahbaz Khan; Fan Zhu; Ling Shao; Gui-Song Xia; Xiang Bai
Description

iSAID contains 655,451 object instances for 15 categories across 2,806 high-resolution images. The images of iSAID is the same as the DOTA-v1.0 dataset, which are manily collected from the Google Earth, some are taken by satellite JL-1, the others are taken by satellite GF-2 of the China Centre for Resources Satellite Data and Application.

Search
Clear search
Close search
Google apps
Main menu