{"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/regionclip-region-based-language-image","title":"RegionCLIP: Region-based Language-Image Pretraining","arxiv_id":"2112.09106","date":"2021-12-16","proceeding":"CVPR 2022 1","authors":["Yiwu Zhong","Jianwei Yang","Pengchuan Zhang","Chunyuan Li","Noel Codella","Liunian Harold Li","Luowei Zhou","Xiyang Dai","Lu Yuan","Yin Li","Jianfeng Gao"],"abstract":"Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations, thus enabling fine-grained alignment between image regions and textual concepts. Our method leverages a CLIP model to match image regions with template captions and then pretrains our model to align these region-text pairs in the feature space. When transferring our pretrained model to the open-vocabulary object detection tasks, our method significantly outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets, respectively. Moreoever, the learned region representations support zero-shot inference for object detection, showing promising results on both COCO and LVIS datasets. Our code is available at https://github.com/microsoft/RegionCLIP.","url_abs":"https://arxiv.org/abs/2112.09106v1","url_pdf":"https://arxiv.org/pdf/2112.09106v1.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":"regionclip-region-based-language-image","repo_url":"https://github.com/microsoft/regionclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"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":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset":"LVIS v1.0","model":"Region-CLIP (RN50x4-C4)","rank_in_archive_order":19,"of":28,"metrics":{"AP novel-LVIS base training":"22.0"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset":"LVIS v1.0","model":"Region-CLIP (RN50-C4)","rank_in_archive_order":26,"of":28,"metrics":{"AP novel-LVIS base training":"17.1"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"Region-CLIP (RN50x4-C4)","rank_in_archive_order":14,"of":32,"metrics":{"AP 0.5":"39.3"},"uses_additional_data":true},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"Region-CLIP (RN50-C4)","rank_in_archive_order":23,"of":32,"metrics":{"AP 0.5":"31.4"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.09106","atlas_url":"https://app.syntology.ai/?focus=2112.09106","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2112.09106"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.09106\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.09106"},"call":"get_concepts_for_paper(arxiv_id=\"2112.09106\")"}],"by_repo":[{"repo":"microsoft/regionclip","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["Zhong_RegionCLIP_Region-Based_Language-Image_Pretraining_CVPR_2022_paper"],"harvested_for_calls":[]}],"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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"06ed72e354cbe0608d357cd04280f77c377be26b0f97b1a3551cb04347c5d3eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}