{"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/localized-vision-language-matching-for-open","title":"Localized Vision-Language Matching for Open-vocabulary Object Detection","arxiv_id":"2205.06160","date":"2022-05-12","proceeding":null,"authors":["Maria A. Bravo","Sudhanshu Mittal","Thomas Brox"],"abstract":"In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a location-guided image-caption matching technique to learn class labels for both novel and known classes in a weakly-supervised manner and second specializes the model for the object detection task using known class annotations. We show that a simple language model fits better than a large contextualized language model for detecting novel objects. Moreover, we introduce a consistency-regularization technique to better exploit image-caption pair information. Our method compares favorably to existing open-vocabulary detection approaches while being data-efficient. Source code is available at https://github.com/lmb-freiburg/locov .","url_abs":"https://arxiv.org/abs/2205.06160v2","url_pdf":"https://arxiv.org/pdf/2205.06160v2.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":"localized-vision-language-matching-for-open","repo_url":"https://github.com/lmb-freiburg/locov","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"open-vocabulary-attribute-detection","task_name":"Open Vocabulary Attribute Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"open-world-object-detection","task_name":"Open World Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open-vocabulary object detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-attribute-detection-on-ovad","task":"Open Vocabulary Attribute Detection","dataset":"OVAD benchmark","model":"LocOv (ResNet50)","rank_in_archive_order":4,"of":5,"metrics":{"mean average precision":"14.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"LocOv (RN50-C4)","rank_in_archive_order":27,"of":32,"metrics":{"AP 0.5":"28.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.06160","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}