{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/grounded-language-image-pre-training","title":"Grounded Language-Image Pre-training","arxiv_id":"2112.03857","date":"2021-12-07","proceeding":"CVPR 2022 1","authors":["Liunian Harold Li","Pengchuan Zhang","Haotian Zhang","Jianwei Yang","Chunyuan Li","Yiwu Zhong","Lijuan Wang","Lu Yuan","Lei Zhang","Jenq-Neng Hwang","Kai-Wei Chang","Jianfeng Gao"],"abstract":"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. Code is released at https://github.com/microsoft/GLIP.","url_abs":"https://arxiv.org/abs/2112.03857v2","url_pdf":"https://arxiv.org/pdf/2112.03857v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"grounded-language-image-pre-training","repo_url":"https://github.com/microsoft/GLIP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"grounded-language-image-pre-training","repo_url":"https://github.com/brown-palm/ObjectPrompt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"grounded-language-image-pre-training","repo_url":"https://github.com/rsCPSyEu/ovd_cod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"described-object-detection","task_name":"Described Object Detection"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"zero-shot-object-detection","task_name":"Zero-Shot Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-object-detection-on-rf100","task":"2D Object Detection","dataset":"RF100","model":"GLIP","rank_in_archive_order":1,"of":1,"metrics":{"Average mAP":"0.112"},"uses_additional_data":false},{"leaderboard":"/sota/described-object-detection-on-description","task":"Described Object Detection","dataset":"Description Detection Dataset","model":"GLIP-T","rank_in_archive_order":4,"of":8,"metrics":{"Intra-scenario ABS mAP":"21.5","Intra-scenario FULL mAP":"19.1","Intra-scenario PRES mAP":"18.3"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-odinw-13","task":"Few-Shot Object Detection","dataset":"ODinW-13","model":"GLIP-T","rank_in_archive_order":3,"of":3,"metrics":{"Average Score":"50.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-odinw-35","task":"Few-Shot Object Detection","dataset":"ODinW-35","model":"GLIP-T","rank_in_archive_order":3,"of":3,"metrics":{"Average Score":"38.9"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"GLIP (Swin-L, multi-scale)","rank_in_archive_order":19,"of":220,"metrics":{"box AP":"60.8"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GLIP (Swin-L, multi-scale)","rank_in_archive_order":23,"of":225,"metrics":{"AP50":"79.5","AP75":"67.7","APL":"75.0","APM":"64.9","APS":"45.3","box mAP":"61.5"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"GLIP-L\n(Swin-L)","rank_in_archive_order":3,"of":45,"metrics":{"Average mAP":"48.0","Effective Robustness":"24.89"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"GLIP-T\n(Swin-T)","rank_in_archive_order":21,"of":45,"metrics":{"Average mAP":"29.1","Effective Robustness":"8.11"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-odinw-full-shot-13-tasks","task":"Object Detection","dataset":"ODinW Full-Shot 13 Tasks","model":"GLIP","rank_in_archive_order":8,"of":8,"metrics":{"AP":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-test","task":"Phrase Grounding","dataset":"Flickr30k Entities Test","model":"GLIP","rank_in_archive_order":3,"of":18,"metrics":{"R@1":"87.1","R@10":"98.1","R@5":"96.9"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 minival","model":"GLIP-L","rank_in_archive_order":7,"of":11,"metrics":{"AP":"37.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0-val","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 val","model":"GLIP-L","rank_in_archive_order":7,"of":9,"metrics":{"AP":"26.9"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.03857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03857"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/GLIP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/brown-palm/ObjectPrompt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rsCPSyEu/ovd_cod","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"525b77c721203779","entry":"create_positive_map","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"525b77c721203779"}},{"code_sha256_prefix":"ea2c188d68558611","entry":"create_positive_map_label_to_token_from_positive_map","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ea2c188d68558611"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}