{"id":804010,"date":"2021-12-11T14:47:35","date_gmt":"2021-12-11T22:47:35","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=804010"},"modified":"2022-05-24T21:04:55","modified_gmt":"2022-05-25T04:04:55","slug":"grounded-language-image-pre-training","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/grounded-language-image-pre-training\/","title":{"rendered":"Grounded Language-Image Pre-training"},"content":{"rendered":"
This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head.<\/p>\n","protected":false},"excerpt":{"rendered":"
This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP […]<\/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":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13562,13545],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[263185],"msr-conference":[262702],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-804010","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-research-area-human-language-technologies","msr-locale-en_us","msr-field-of-study-computer-vision-and-pattern-recognition"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2022-6-7","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\/pdf\/2112.03857.pdf","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Liunian Harold Li","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Pengchuan Zhang","user_id":36587,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Pengchuan Zhang"},{"type":"text","value":"Haotian Zhang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Jianwei Yang","user_id":40261,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jianwei Yang"},{"type":"user_nicename","value":"Chunyuan Li","user_id":37971,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Chunyuan Li"},{"type":"text","value":"Yiwu Zhong","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Lijuan Wang","user_id":32680,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lijuan Wang"},{"type":"user_nicename","value":"Lu Yuan","user_id":32755,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lu Yuan"},{"type":"text","value":"Lei Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Jenq-Neng Hwang","user_id":0,"rest_url":false},{"type":"text","value":"Kai-Wei Chang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Jianfeng Gao","user_id":32246,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jianfeng Gao"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[844516],"msr_group":[144931],"msr_project":[689814],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":689814,"post_title":"Project Florence-VL","post_name":"project-florence-vl","post_type":"msr-project","post_date":"2020-09-22 21:43:29","post_modified":"2022-08-24 10:56:02","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/project-florence-vl\/","post_excerpt":"Microsoft Azure Florence-VL aims to develop state-of-the-art vision-language learning technologies to endow computers with an ability to effectively learn from multi-modality data.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/689814"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/804010"}],"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\/804010\/revisions"}],"predecessor-version":[{"id":804016,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/804010\/revisions\/804016"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=804010"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=804010"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=804010"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=804010"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=804010"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=804010"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=804010"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=804010"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=804010"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=804010"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=804010"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=804010"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=804010"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=804010"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=804010"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=804010"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}