{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/2112.03857","atlas_url":"https://app.syntology.ai/?focus=2112.03857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03857"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.03857"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.03857"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.03857\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2112.03857"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.03857\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.03857"},"call":"get_concepts_for_paper(arxiv_id=\"2112.03857\")"}],"by_repo":[{"repo":"microsoft/GLIP","kind":"official","samples":2,"ran":2,"instrument":1,"unverified":0,"placed_by_identical_code":2},{"repo":"brown-palm/ObjectPrompt","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.00180"],"harvested_for_calls":[{"arxiv_id":"2311.00180","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.00180"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.00180\")"}]},{"repo":"rsCPSyEu/ovd_cod","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2112.03857.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2112.03857.svg"},"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},"n_samples":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":2,"n_ran_checked":1,"n_instrument":1,"repositories":1}},"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":0,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"525b77c721203779","code_sha256_prefix":"525b77c721203779","entry":"create_positive_map","repo":null,"repo_kind":"official","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,"signature":"tokenized:MockTokenized/0/?, tokens_positive:list/1/list","fixture_out_type":"Tensor","code_page":"/code/create-positive-map","census":null,"placed_by_identical_code":{"repo":"microsoft/GLIP","path":"maskrcnn_benchmark/engine/predictor_glip.py","file_url":"https://github.com/microsoft/glip/blob/HEAD/maskrcnn_benchmark/engine/predictor_glip.py","papers":["2206.05836"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"525b77c721203779"}},{"code_sha256":"ea2c188d68558611","code_sha256_prefix":"ea2c188d68558611","entry":"create_positive_map_label_to_token_from_positive_map","repo":null,"repo_kind":"official","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,"signature":"positive_map:Tensor/2/float, plus:int/0/int","fixture_out_type":"dict","retrieve_with":{"tool":"get_code","code_sha256":"ea2c188d68558611"},"code_page":null,"census":null,"placed_by_identical_code":{"repo":"microsoft/GLIP","path":"maskrcnn_benchmark/engine/predictor_glip.py","file_url":"https://github.com/microsoft/glip/blob/HEAD/maskrcnn_benchmark/engine/predictor_glip.py","papers":["2206.05836"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"ea2c188d68558611"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a732a4fcd2a7061bf7d25fa53415760c93d9dc33e95ab05645a80b10237b20a7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}