{"id":936363,"date":"2023-04-24T09:31:15","date_gmt":"2023-04-24T16:31:15","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/"},"modified":"2023-04-24T09:31:15","modified_gmt":"2023-04-24T16:31:15","slug":"mask-conditional-synthetic-satellite-imagery","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/mask-conditional-synthetic-satellite-imagery\/","title":{"rendered":"Mask Conditional Synthetic Satellite Imagery"},"content":{"rendered":"

In this paper we propose a mask-conditional synthetic image generation model for creating synthetic satellite imagery datasets. Given a dataset of real high-resolution images and accompanying land cover masks, we show that it is possible to train an upstream conditional synthetic imagery generator, use that generator to create synthetic imagery with the land cover masks, then train a downstream model on the synthetic imagery and land cover masks that achieves similar test performance to a model that was trained with the real imagery. Further, we find that incorporating a mixture of real and synthetic imagery acts as a data augmentation method, producing better models than using only real imagery (0.5834 vs. 0.5235 mIoU). Finally, we find that encouraging diversity of outputs in the upstream model is a necessary component for improved downstream task performance. We have released code for reproducing our work on GitHub, see https:\/\/github.com\/ms-synthetic-satellite-image\/synthetic-satellite-imagery (opens in new tab)<\/span><\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"

In this paper we propose a mask-conditional synthetic image generation model for creating synthetic satellite imagery datasets. Given a dataset of real high-resolution images and accompanying land cover masks, we show that it is possible to train an upstream conditional synthetic imagery generator, use that generator to create synthetic imagery with the land cover masks, […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"ICLR 2023 Machine Learning for Remote Sensing Workshop","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2023-5-5","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"https:\/\/nasaharvest.github.io\/ml-for-remote-sensing\/iclr2023\/","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246691,246688],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-936363","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us","msr-field-of-study-computer-science","msr-field-of-study-computer-vision"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2023-5-5","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2302.04305","label_id":"243109","label":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Van Anh Le","user_id":0,"rest_url":false},{"type":"text","value":"Varshini Reddy","user_id":0,"rest_url":false},{"type":"text","value":"Zixi Chen","user_id":0,"rest_url":false},{"type":"text","value":"Mengyuan Li","user_id":0,"rest_url":false},{"type":"text","value":"Xinran Tang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Anthony Ortiz","user_id":39715,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Anthony Ortiz"},{"type":"user_nicename","value":"Simone Fobi Nsutezo","user_id":41988,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Simone Fobi Nsutezo"},{"type":"user_nicename","value":"Caleb Robinson","user_id":39606,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Caleb Robinson"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[696544],"msr_project":[1014747,812350],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":1014747,"post_title":"Fundamental Rights - AI for Good","post_name":"fundamental-rights-ai-for-good","post_type":"msr-project","post_date":"2024-04-02 08:58:55","post_modified":"2024-09-19 09:50:54","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/fundamental-rights-ai-for-good\/","post_excerpt":"Microsoft is committed to strengthening communities and empowering the organizations that help them thrive. We have a responsibility to protect people\u2019s fundamental rights, and help all communities succeed.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1014747"}]}},{"ID":812350,"post_title":"Geospatial Machine Learning","post_name":"geospatial-machine-learning","post_type":"msr-project","post_date":"2022-02-24 10:03:45","post_modified":"2024-04-19 14:52:45","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/geospatial-machine-learning\/","post_excerpt":"We combine geospatial data with machine learning in collaboration with partners at universities, conservation agencies, and NGOs in projects that support disaster response, humanitarian action and conservation efforts.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/812350"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/936363","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/936363\/revisions"}],"predecessor-version":[{"id":936366,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/936363\/revisions\/936366"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=936363"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=936363"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=936363"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=936363"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=936363"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=936363"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=936363"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=936363"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=936363"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=936363"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=936363"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=936363"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=936363"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}