{"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/glipv2-unifying-localization-and-vision","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","arxiv_id":"2206.05836","date":"2022-06-12","proceeding":null,"authors":["Haotian Zhang","Pengchuan Zhang","Xiaowei Hu","Yen-Chun Chen","Liunian Harold Li","Xiyang Dai","Lijuan Wang","Lu Yuan","Jenq-Neng Hwang","Jianfeng Gao"],"abstract":"We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (VLP) with three pre-training tasks: phrase grounding as a VL reformulation of the detection task, region-word contrastive learning as a novel region-word level contrastive learning task, and the masked language modeling. This unification not only simplifies the previous multi-stage VLP procedure but also achieves mutual benefits between localization and understanding tasks. Experimental results show that a single GLIPv2 model (all model weights are shared) achieves near SoTA performance on various localization and understanding tasks. The model also shows (1) strong zero-shot and few-shot adaption performance on open-vocabulary object detection tasks and (2) superior grounding capability on VL understanding tasks. Code will be released at https://github.com/microsoft/GLIP.","url_abs":"https://arxiv.org/abs/2206.05836v2","url_pdf":"https://arxiv.org/pdf/2206.05836v2.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":"glipv2-unifying-localization-and-vision","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"}}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open-vocabulary object detection"},{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GLIPv2 (CoSwin-H, multi-scale)","rank_in_archive_order":21,"of":225,"metrics":{"box mAP":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-minival","task":"Object Detection","dataset":"LVIS v1.0 minival","model":"GLIPv2","rank_in_archive_order":6,"of":6,"metrics":{"box AP":"59.8"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-on-odinw-full-shot-13-tasks","task":"Object Detection","dataset":"ODinW Full-Shot 13 Tasks","model":"GLIPv2","rank_in_archive_order":7,"of":8,"metrics":{"AP":"70.4"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-test","task":"Phrase Grounding","dataset":"Flickr30k Entities Test","model":"GLIPv2","rank_in_archive_order":1,"of":18,"metrics":{"R@1":"87.7"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on","task":"Referring Expression Segmentation","dataset":"PhraseCut","model":"GLIPv2","rank_in_archive_order":1,"of":6,"metrics":{"Mean IoU":"61.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.05836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05836"}},"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":"deterministic:regex_extraction","url":"https://github.com/microsoft/GLIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"525b77c721203779","entry":"create_positive_map","repo":"microsoft/glip","repo_kind":"official","path":"maskrcnn_benchmark/engine/predictor_glip.py","file_url":"https://github.com/microsoft/glip/blob/HEAD/maskrcnn_benchmark/engine/predictor_glip.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"525b77c721203779"}},{"code_sha256_prefix":"ea2c188d68558611","entry":"create_positive_map_label_to_token_from_positive_map","repo":"microsoft/glip","repo_kind":"official","path":"maskrcnn_benchmark/engine/predictor_glip.py","file_url":"https://github.com/microsoft/glip/blob/HEAD/maskrcnn_benchmark/engine/predictor_glip.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea2c188d68558611"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}